![](/catalog-art/models-header.webp)

1.  [](/)
2.  [Catalog](/catalog)
3.  [Models](/models)

# Models

Embedding, detection, classification, transcription and multimodal models: what each is good at, its inputs and outputs, and how it runs on Mixpeek.

For agents`Read every Mixpeek model record (inputs, outputs, license, how it runs, templates that use it) as JSON at https://mixpeek.com/models.json, or one model at https://mixpeek.com/models/<id>.json. No key needed.`Copy

Search models by name, task, or capability...⌘K

[Build with a model](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=models_index&utm_campaign=mvs_onramp) [Model registry docs](/docs/processing/model-registry)

All modelsEmbeddingDetectionSegmentationVideo and image Q&AGenerationClassificationFaceTranscriptionReranking

## Filters

Reset

Task

*   Embedding52
*   Detection13
*   Segmentation9
*   Classification5
*   Video and image Q&A6
*   Transcription2
*   Show all 9

Use case

*   Visual search35
*   Text search7
*   Multilingual search7
*   Product search25
*   Fashion3
*   Brand detection10
*   Show all 24

Input

Provider

Deployment

License

Filters

97 models

Sort:Most usedNameNewest releaseMost templatesMost namespacesVector dimensionsSmallestFastest cold start

*   ### [Multilingual E5 Large Instruct](/models/multilingual-e5-large-instruct)
    
    intfloat
    
    Hosted
    
    Default text vector for search over transcripts, OCR text, descriptions, documents and web pages in 100+ languages; one space for query and passage text.
    
    EmbeddingText
    
*   ### [Gemini Embedding 2](/models/gemini-embedding-2)
    
    Google
    
    Provider API
    
    One vector space for video segments, images, PDFs, audio and text queries; the default for object-level multimodal extractors (multimodal\_extractor v2, universal\_extractor).
    
    EmbeddingMultimodal
    
*   ### [all-MiniLM-L6-v2](/models/all-minilm-l6-v2)
    
    Sentence Transformers
    
    Hosted
    
    Small, fast English sentence vectors on CPU (22M params, 384 dims) for short text, dedup and clustering.
    
    EmbeddingText
    
*   ### [Vertex AI multimodalembedding@001](/models/multimodalembedding)
    
    Google
    
    Provider API
    
    Category-level text-to-video and text-to-image search in one 1408-d space (committed mAP 0.855 on a 10-video text eval).
    
    EmbeddingMultimodal
    
*   ### [SigLIP Base patch16 224](/models/siglip-base-patch16-224)
    
    Google
    
    Hosted
    
    Text-to-image and image-to-image search over photos, products and video frames in one shared space.
    
    EmbeddingMultimodal
    
*   ### [InsightFace buffalo\_l (SCRFD-10GF + ArcFace ResNet50 WebFace600K)](/models/insightface-buffalo-l)
    
    InsightFace
    
    Hosted
    
    Face detection, 5-point alignment and 512-d face identity vectors for finding the same person across images and video frames.
    
    FaceMultimodal
    
*   ### [InsightFace buffalo\_sc (SCRFD-500MF + MobileFaceNet WebFace600K)](/models/insightface-buffalo-sc)
    
    InsightFace
    
    Hosted
    
    The fastest face detector option (SCRFD-500MF) for high-volume frames where small faces matter less.
    
    FaceMultimodal
    
*   ### [LAION CLAP HTSAT-tiny (630k-audioset-best)](/models/clap-htsat-tiny)
    
    lukewys
    
    Hosted
    
    Sound-alike search over short audio windows (jingles, music beds, effects) and text-to-audio search ("upbeat jingle with bells") in one 512-d space.
    
    EmbeddingMultimodal
    
*   ### [DINOv2 Base](/models/dinov2-base)
    
    Meta
    
    Hosted
    
    Image-to-image similarity on visual structure (layout, near-duplicates, the same object or scene) with no text in the loop.
    
    EmbeddingImage
    
*   ### [Jina Embeddings v2 Base Code](/models/jina-embeddings-v2-base-code)
    
    Jina AI
    
    Hosted
    
    Code snippets and natural-language-to-code search across about 30 programming languages, with up to 8192-token inputs (ALiBi).
    
    EmbeddingText
    
*   ### [Gemini 2.5 Flash](/models/gemini-2-5-flash)
    
    Google
    
    Provider API
    
    The extractors' default for structured extraction and vision work: video description and OCR in multimodal\_extractor v2, web page extraction, PDF layout (document\_graph), scrolling-text OCR.
    
    GenerationMultimodal
    
*   ### [Gemini 3.6 Flash](/models/gemini-3-6-flash)
    
    Google
    
    Provider API
    
    High-quality video QA and structured tagging.
    
    Video and image Q&AMultimodal
    
*   ### [SigLIP so400m patch14 (224/384)](/models/siglip-so400m-patch14-384)
    
    Google
    
    Custom plugin
    
    Strongest SigLIP v1 image-text model; the vision tower behind many VLMs (PaliGemma).
    
    EmbeddingMultimodal
    
*   ### [ColBERTv2](/models/colbertv2-0)
    
    ColBERT
    
    Hosted
    
    Late-interaction text retrieval and reranking (MaxSim over one 128-d vector per token); strong on out-of-domain and term-heavy queries.
    
    EmbeddingText
    
*   ### [TypeSafe Jev](/models/typesafe-jev)
    
    typesafe-system-one
    
    Provider API
    
    Typed decisions with calibrated probabilities over a JSON state: yes/no relevance for rerank, label probabilities for classify, closed-set schema fields for text\_extractor; the platform's DECISION\_MODEL\_DEFAULT.
    
    ClassificationMultimodal
    
*   ### [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite)
    
    Google
    
    Provider API
    
    Low-cost bulk tagging of scenes and frames.
    
    Video and image Q&AMultimodal
    
*   ### [BGE Reranker v2 M3](/models/bge-reranker-v2-m3)
    
    BAAI
    
    Hosted
    
    Re-ordering a short candidate list of text documents against a query (cross-encoder, multilingual), most useful where the dense ordering is weak.
    
    RerankingText
    
*   ### [ColQwen2 v1.0 (merged)](/models/colqwen2-v1-0-merged)
    
    ColPali
    
    Hosted
    
    Text search over document page images (PDF pages, slides, infographics, tables) by late interaction, with no OCR step.
    
    EmbeddingMultimodal
    
*   ### [Falconsai NSFW image detection (ViT)](/models/nsfw-image-detection)
    
    Falconsai
    
    Hosted
    
    Fast binary normal/nsfw screening of images, and of video by the max score over sparse sampled frames.
    
    ClassificationMultimodal
    
*   ### [Whisper large-v3-turbo](/models/whisper-large-v3-turbo)
    
    OpenAI
    
    Hosted
    
    Multilingual speech-to-text on GPU at large-v3 quality with the decoder cut from 32 to 4 layers, so decoding is much faster than large-v3.
    
    TranscriptionMultimodal
    
*   ### [DistilBERT NSFW text classifier](/models/distilbert-nsfw-text-classifier)
    
    eliasalbouzidi
    
    Hosted
    
    Cheap binary safe/nsfw screening of English text such as captions, titles and transcripts.
    
    ClassificationText
    
*   ### [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite)
    
    Google
    
    Provider API
    
    The platform's default LLM (DEFAULT\_GEMINI\_MODEL) for cheap per-document work in retriever stages (enrich, filter, summarize) and for video-segment description and OCR in multimodal\_extractor v1.
    
    GenerationMultimodal
    
*   ### [OpenCLIP ViT-L/14 LAION-2B s32B b82K](/models/clip-vit-l-14-laion2b-s32b-b82k)
    
    LAION
    
    Hosted
    
    Image-to-image similarity from a large web-trained ViT-L/14 image tower.
    
    EmbeddingImage
    
*   ### [SigLIP 2 so400m patch14 (224/384)](/models/siglip2-so400m-patch14-384)
    
    Google
    
    Custom plugin
    
    Logos, signage, brands and venue shots in concert footage (the visual arm of an internal eval); strongest SigLIP 2 below giant.
    
    EmbeddingMultimodal
    

Page 1 of 5

Or let Mixpeek choose

## Not sure which model fits? Describe your data instead.

Say what your files are and what you want from them. Mixpeek writes the namespace for you, with the extractors, models and retrievers, checks it against the catalog and prices it before you apply it.

To go further, the manifest loop tries other models, settings and retriever pipelines, scores each one on labelled examples it holds back, and hands you the best as a manifest you can deploy.

[How it works](/docs/processing/autonomous-namespaces) [POST /v1/manifest/generate](/docs/api-reference/manifest/generate-manifest)

## Questions

Which of these models does Mixpeek run today?

15 are hosted on Mixpeek as Ray Serve apps (Multilingual E5 Large Instruct, all-MiniLM-L6-v2, SigLIP Base patch16 224, InsightFace buffalo\_l (SCRFD-10GF + ArcFace ResNet50 WebFace600K), InsightFace buffalo\_sc (SCRFD-500MF + MobileFaceNet WebFace600K) and others). 13 are provider APIs Mixpeek calls by name. 41 can run as a custom plugin and do not run yet. 28 are blocked today; each page says why.

How is the default order decided?

By usage, the namespaces and collections that use each model, counted on 2026-11-06T13:42:25Z, then by how many templates use it, whether it runs today and whether we have our own evaluation.

What does unmeasured mean on a model?

We have not measured that model's cost or quality on our own image and data yet. Publisher benchmarks are linked from the model's sources and are not copied into the measured fields.

Can an agent read this catalog?

Yes. /models.json holds every record and /models/<id>.json holds one. They are the same records this page renders, generated from the catalog the Mixpeek server is built from.

How do I use a model in a namespace?

Open the model and deploy a template that already uses it, or add it to a new or existing namespace from the Designer in Studio. Inference is billed per unit you process, so a namespace is not billed for inference while it sits idle.

## All catalog models

*   [Multilingual E5 Large Instruct](/models/multilingual-e5-large-instruct)
*   [Gemini Embedding 2](/models/gemini-embedding-2)
*   [all-MiniLM-L6-v2](/models/all-minilm-l6-v2)
*   [Vertex AI multimodalembedding@001](/models/multimodalembedding)
*   [SigLIP Base patch16 224](/models/siglip-base-patch16-224)
*   [InsightFace buffalo\_l (SCRFD-10GF + ArcFace ResNet50 WebFace600K)](/models/insightface-buffalo-l)
*   [InsightFace buffalo\_sc (SCRFD-500MF + MobileFaceNet WebFace600K)](/models/insightface-buffalo-sc)
*   [LAION CLAP HTSAT-tiny (630k-audioset-best)](/models/clap-htsat-tiny)
*   [DINOv2 Base](/models/dinov2-base)
*   [Jina Embeddings v2 Base Code](/models/jina-embeddings-v2-base-code)
*   [Gemini 2.5 Flash](/models/gemini-2-5-flash)
*   [Gemini 3.6 Flash](/models/gemini-3-6-flash)
*   [SigLIP so400m patch14 (224/384)](/models/siglip-so400m-patch14-384)
*   [ColBERTv2](/models/colbertv2-0)
*   [TypeSafe Jev](/models/typesafe-jev)
*   [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite)
*   [BGE Reranker v2 M3](/models/bge-reranker-v2-m3)
*   [ColQwen2 v1.0 (merged)](/models/colqwen2-v1-0-merged)
*   [Falconsai NSFW image detection (ViT)](/models/nsfw-image-detection)
*   [Whisper large-v3-turbo](/models/whisper-large-v3-turbo)
*   [DistilBERT NSFW text classifier](/models/distilbert-nsfw-text-classifier)
*   [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite)
*   [OpenCLIP ViT-L/14 LAION-2B s32B b82K](/models/clip-vit-l-14-laion2b-s32b-b82k)
*   [SigLIP 2 so400m patch14 (224/384)](/models/siglip2-so400m-patch14-384)
*   [bge-small-en-v1.5](/models/bge-small-en-v1-5)
*   [AuraFace v1 (SCRFD-10GF + ArcFace-style ResNet100)](/models/auraface-v1)
*   [Claude Sonnet 4.5](/models/claude-sonnet-4-5)
*   [D-FINE L (COCO)](/models/d-fine-l-coco)
*   [Gemini 2.5 Flash-Lite](/models/gemini-2-5-flash-lite)
*   [Gemini 3 Flash (preview)](/models/gemini-3-flash-preview)
*   [Gemini 3.8 Flash](/models/gemini-3-8-flash)
*   [GPT-4o mini](/models/gpt-4o-mini)
*   [Grounding DINO Tiny](/models/grounding-dino-tiny)
*   [OpenAI Whisper API (whisper-1)](/models/whisper-1)
*   [Qwen3 Embedding 0.6B](/models/qwen3-embedding-0-6b)
*   [SAM 2.1 Hiera Tiny (small, base-plus)](/models/sam2-1-hiera-tiny)
*   [DFN2B CLIP ViT-L/14](/models/dfn2b-clip-vit-l-14)
*   [DFN5B CLIP ViT-H/14](/models/dfn5b-clip-vit-h-14)
*   [FashionCLIP (2.0)](/models/fashion-clip)
*   [Marqo-FashionCLIP](/models/marqo-fashionclip)
*   [Marqo-FashionSigLIP](/models/marqo-fashionsiglip)
*   [MetaCLIP ViT-H/14 (2.5B)](/models/metaclip-h14-fullcc2-5b)
*   [OpenAI CLIP ViT-B/16](/models/clip-vit-base-patch16)
*   [OpenAI CLIP ViT-B/32](/models/clip-vit-base-patch32)
*   [OpenAI CLIP ViT-L/14](/models/clip-vit-large-patch14)
*   [OpenCLIP ViT-B/16 LAION-2B](/models/clip-vit-b-16-laion2b-s34b-b88k)
*   [OpenCLIP ViT-B/32 LAION-2B](/models/clip-vit-b-32-laion2b-s34b-b79k)
*   [OpenCLIP ViT-bigG/14 LAION-2B](/models/clip-vit-bigg-14-laion2b-39b-b160k)
*   [OpenCLIP ViT-H/14 LAION-2B](/models/clip-vit-h-14-laion2b-s32b-b79k)
*   [RF-DETR Base](/models/rf-detr-base)
*   [RT-DETR R50vd](/models/rtdetr-r50vd)
*   [RT-DETRv2 R50vd](/models/rtdetr-v2-r50vd)
*   [SAM 2.1 Hiera Large](/models/sam2-1-hiera-large)
*   [SigLIP 2 Base patch16 (224/256/384/512, patch32-256)](/models/siglip2-base-patch16-224)
*   [SigLIP 2 Base patch16 NaFlex](/models/siglip2-base-patch16-naflex)
*   [SigLIP 2 giant-opt patch16 (256/384)](/models/siglip2-giant-opt-patch16-384)
*   [SigLIP 2 Large patch16 (256/384/512)](/models/siglip2-large-patch16-384)
*   [SigLIP 2 so400m patch16 (256/384/512)](/models/siglip2-so400m-patch16-384)
*   [SigLIP 2 so400m patch16 NaFlex](/models/siglip2-so400m-patch16-naflex)
*   [SigLIP Base patch16 (256/384/512)](/models/siglip-base-patch16-384)
*   [SigLIP Base patch16 256 multilingual](/models/siglip-base-patch16-256-multilingual)
*   [SigLIP Large patch16 (256/384)](/models/siglip-large-patch16-384)
*   [SigLIP so400m patch16 256 i18n](/models/siglip-so400m-patch16-256-i18n)
*   [V-JEPA 2 VITG](/models/vjepa2-vitg-fpc64-256)
*   [V-JEPA 2 VITL](/models/vjepa2-vitl-fpc64-256)
*   [X-CLIP base-patch16](/models/xclip-base-patch16)
*   [X-CLIP base-patch32](/models/xclip-base-patch32)
*   [X-CLIP large-patch14](/models/xclip-large-patch14)
*   [YOLOX-S](/models/yolox-s)
*   [EfficientSAM ViT-S](/models/efficientsam-vits)
*   [InternVideo2 Stage2 1B (224p, 4 frames)](/models/internvideo2-stage2-1b-224p-f4)
*   [InternVideo2 Stage2 6B](/models/internvideo2-stage2-6b)
*   [InternVideo2.5 Chat 8B](/models/internvideo2-5-chat-8b)
*   [MobileCLIP (S0, S1, S2, B)](/models/mobileclip)
*   [MobileCLIP2 (S0, S2, S4, B, L-14)](/models/mobileclip2)
*   [MobileSAM](/models/mobilesam)
*   [OpenAI CLIP ViT-L/14 336](/models/clip-vit-large-patch14-336)
*   [OpenCLIP ViT-B/16 DataComp-1B](/models/clip-vit-b-16-datacomp-xl-s13b-b90k)
*   [OpenCLIP ViT-L/14 DataComp-1B](/models/clip-vit-l-14-datacomp-xl-s13b-b90k)
*   [Qwen2.5 7B Instruct](/models/qwen2-5-7b-instruct)
*   [Qwen2.5-VL 7B Instruct](/models/qwen2-5-vl-7b-instruct)
*   [SAM 3 (Segment Anything with Concepts)](/models/sam3)
*   [Ultralytics YOLO11 classify](/models/yolo11-classify)
*   [Ultralytics YOLO11 detect](/models/yolo11-detect)
*   [Ultralytics YOLO11 pose](/models/yolo11-pose)
*   [Ultralytics YOLO11 segment](/models/yolo11-segment)
*   [Ultralytics YOLO26 classify](/models/yolo26-classify)
*   [Ultralytics YOLO26 detect](/models/yolo26-detect)
*   [Ultralytics YOLO26 pose](/models/yolo26-pose)
*   [Ultralytics YOLO26 segment](/models/yolo26-segment)
*   [Ultralytics YOLOv8 detect](/models/yolov8-detect)
*   [Ultralytics YOLOv8 pose](/models/yolov8-pose)
*   [Ultralytics YOLOv8 segment](/models/yolov8-segment)
*   [VideoPrism Base (16 frames, 288px)](/models/videoprism-base-f16r288)
*   [VideoPrism LvT Base (video-text, 16 frames, 288px)](/models/videoprism-lvt-base-f16r288)
*   [YOLO-World v2 (Ultralytics)](/models/yolo-world-v2)
*   [YOLOE-11 (text, visual and prompt-free)](/models/yoloe-11-segment)

## Hugging Face model directory

Directory pages for 436 public models. They are not in the catalog above, and Mixpeek does not run them as listed.

*   [ahmed-masry/ColMate-3B](/model/ahmed-masry/ColMate-3B)
*   [ai-sage/GigaAM-Multilingual](/model/ai-sage/GigaAM-Multilingual)
*   [AIDC-AI/Ovis2.6-30B-A3B](/model/AIDC-AI/Ovis2.6-30B-A3B)
*   [AILab-CVC/YOLO-World-L](/model/AILab-CVC/YOLO-World-L)
*   [Alibaba-NLP/gme-Qwen2-VL-2B-Instruct](/model/Alibaba-NLP/gme-Qwen2-VL-2B-Instruct)
*   [Alibaba-NLP/gte-large-en-v1.5](/model/Alibaba-NLP/gte-large-en-v1.5)
*   [Alibaba-NLP/gte-modernbert-base](/model/Alibaba-NLP/gte-modernbert-base)
*   [Alibaba-NLP/gte-multilingual-base](/model/Alibaba-NLP/gte-multilingual-base)
*   [Alibaba-NLP/gte-reranker-modernbert-base](/model/Alibaba-NLP/gte-reranker-modernbert-base)
*   [Alibaba-NLP/GVE-3B](/model/Alibaba-NLP/GVE-3B)
*   [Alibaba-VELLDEPTH/CTVG-4B](/model/Alibaba-VELLDEPTH/CTVG-4B)
*   [allenai/Molmo2-8B](/model/allenai/Molmo2-8B)
*   [allenai/olmOCR-2-7B-1025](/model/allenai/olmOCR-2-7B-1025)
*   [amazon/chronos-2](/model/amazon/chronos-2)
*   [amazon/chronos-bolt-base](/model/amazon/chronos-bolt-base)
*   [amazon/patchcore-resnet50](/model/amazon/patchcore-resnet50)
*   [apple/aimv2-3B-patch14-448](/model/apple/aimv2-3B-patch14-448)
*   [apple/AIMv2-large-patch14-native](/model/apple/AIMv2-large-patch14-native)
*   [apple/DepthPro](/model/apple/DepthPro)
*   [apple/FastVLM-0.5B](/model/apple/FastVLM-0.5B)
*   [apple/FastVLM-7B](/model/apple/FastVLM-7B)
*   [ATH-MaaS/Ovis-Omni-Embedding-3B](/model/ATH-MaaS/Ovis-Omni-Embedding-3B)
*   [ATH-MaaS/Ovis-VL-Embedding-2B](/model/ATH-MaaS/Ovis-VL-Embedding-2B)
*   [ATH-MaaS/Ovis-VL-Embedding-9B](/model/ATH-MaaS/Ovis-VL-Embedding-9B)
*   [athrael-soju/ColUltraVBERT](/model/athrael-soju/ColUltraVBERT)
*   [autotrust/JEV-27B-VL](/model/autotrust/JEV-27B-VL)
*   [BAAI/bge-base-en-v1.5](/model/BAAI/bge-base-en-v1.5)
*   [BAAI/bge-large-en-v1.5](/model/BAAI/bge-large-en-v1.5)
*   [BAAI/bge-m3](/model/BAAI/bge-m3)
*   [BAAI/bge-multilingual-gemma2](/model/BAAI/bge-multilingual-gemma2)
*   [BAAI/bge-reranker-v2.5-gemma2-lightweight](/model/BAAI/bge-reranker-v2.5-gemma2-lightweight)
*   [BAAI/BGE-VL-base](/model/BAAI/BGE-VL-base)
*   [BAAI/BGE-VL-v1.5-zs](/model/BAAI/BGE-VL-v1.5-zs)
*   [BAAI/EVA02-CLIP-L-14-336](/model/BAAI/EVA02-CLIP-L-14-336)
*   [baidu/Qianfan-OCR](/model/baidu/Qianfan-OCR)
*   [baidu/Unlimited-OCR](/model/baidu/Unlimited-OCR)
*   [baidu/Unlimited-OCR-2](/model/baidu/Unlimited-OCR-2)
*   [BidirLM/BidirLM-Omni-2.5B-Embedding](/model/BidirLM/BidirLM-Omni-2.5B-Embedding)
*   [briaai/RMBG-1.4](/model/briaai/RMBG-1.4)
*   [briaai/RMBG-2.0](/model/briaai/RMBG-2.0)
*   [bytedance-research/Lance](/model/bytedance-research/Lance)
*   [bytedance-research/Vidi-7B](/model/bytedance-research/Vidi-7B)
*   [ByteDance/Dolphin-v2](/model/ByteDance/Dolphin-v2)
*   [Cactus-Compute/mirage](/model/Cactus-Compute/mirage)
*   [Cactus-Compute/whistle](/model/Cactus-Compute/whistle)
*   [CIDAS/clipseg-rd64-refined](/model/CIDAS/clipseg-rd64-refined)
*   [Cloudflare/clef](/model/Cloudflare/clef)
*   [Cloudflare/clef-flash](/model/Cloudflare/clef-flash)
*   [Cloudflare/clef-omni](/model/Cloudflare/clef-omni)
*   [codefuse-ai/F2LLM-v2-14B](/model/codefuse-ai/F2LLM-v2-14B)
*   [Cognitive-Lab/ColNetraEmbed](/model/Cognitive-Lab/ColNetraEmbed)
*   [CohereLabs/cohere-transcribe-03-2026](/model/CohereLabs/cohere-transcribe-03-2026)
*   [CohereLabs/cohere-transcribe-arabic-07-2026](/model/CohereLabs/cohere-transcribe-arabic-07-2026)
*   [CohereLabs/command-a-plus-05-2026-bf16](/model/CohereLabs/command-a-plus-05-2026-bf16)
*   [ContextualAI/ctxl-rerank-v2-instruct-multilingual-1b](/model/ContextualAI/ctxl-rerank-v2-instruct-multilingual-1b)
*   [Contrastive-LM/CLM-v0.1-8B](/model/Contrastive-LM/CLM-v0.1-8B)
*   [convaiinnovations/laya](/model/convaiinnovations/laya)
*   [cross-encoder/ettin-reranker-150m-v1](/model/cross-encoder/ettin-reranker-150m-v1)
*   [cross-encoder/ettin-reranker-17m-v1](/model/cross-encoder/ettin-reranker-17m-v1)
*   [cross-encoder/ettin-reranker-1b-v1](/model/cross-encoder/ettin-reranker-1b-v1)
*   [cross-encoder/ettin-reranker-32m-v1](/model/cross-encoder/ettin-reranker-32m-v1)
*   [cross-encoder/ettin-reranker-400m-v1](/model/cross-encoder/ettin-reranker-400m-v1)
*   [cross-encoder/ettin-reranker-68m-v1](/model/cross-encoder/ettin-reranker-68m-v1)
*   [cross-encoder/ms-marco-MiniLM-L6-v2](/model/cross-encoder/ms-marco-MiniLM-L6-v2)
*   [DAMO-NLP-SG/VideoLLaMA3-7B](/model/DAMO-NLP-SG/VideoLLaMA3-7B)
*   [Datadog/Toto-2.0-2.5B](/model/Datadog/Toto-2.0-2.5B)
*   [datalab-to/chandra-ocr-2](/model/datalab-to/chandra-ocr-2)
*   [datalab-to/indra-ocr](/model/datalab-to/indra-ocr)
*   [deepinsight/insightface-retinaface-r50](/model/deepinsight/insightface-retinaface-r50)
*   [deepseek-ai/DeepSeek-OCR-2](/model/deepseek-ai/DeepSeek-OCR-2)
*   [deepseek-ai/DeepSeek-V4-Flash-Vision-Exp](/model/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp)
*   [deepseek-ai/DeepSeek-V4.1-Flash](/model/deepseek-ai/DeepSeek-V4.1-Flash)
*   [deepseek-ai/deepseek-vl2-small](/model/deepseek-ai/deepseek-vl2-small)
*   [depth-anything/DA3-LARGE-1.1](/model/depth-anything/DA3-LARGE-1.1)
*   [depth-anything/DA3-SMALL](/model/depth-anything/DA3-SMALL)
*   [depth-anything/DA3NESTED-GIANT-LARGE-1.1](/model/depth-anything/DA3NESTED-GIANT-LARGE-1.1)
*   [depth-anything/Depth-Anything-V2-Large](/model/depth-anything/Depth-Anything-V2-Large)
*   [distil-whisper/distil-large-v3](/model/distil-whisper/distil-large-v3)
*   [dmis-lab/UltraBERT-Embed-150M](/model/dmis-lab/UltraBERT-Embed-150M)
*   [docling-project/docling-layout-heron](/model/docling-project/docling-layout-heron)
*   [docling-project/docling-models](/model/docling-project/docling-models)
*   [docling-project/SmolDocling-256M-preview](/model/docling-project/SmolDocling-256M-preview)
*   [Edge0/Audio8-ASR-Infinite](/model/Edge0/Audio8-ASR-Infinite)
*   [facebook/detr-resnet-50](/model/facebook/detr-resnet-50)
*   [facebook/dinov2-large](/model/facebook/dinov2-large)
*   [facebook/dinov3-convnext-large-pretrain-lvd1689m](/model/facebook/dinov3-convnext-large-pretrain-lvd1689m)
*   [facebook/dinov3-large](/model/facebook/dinov3-large)
*   [facebook/dinov3-vit7b16-pretrain-lvd1689m](/model/facebook/dinov3-vit7b16-pretrain-lvd1689m)
*   [facebook/dinov3-vitb16-pretrain-lvd1689m](/model/facebook/dinov3-vitb16-pretrain-lvd1689m)
*   [facebook/dinov3-vitl16-pretrain-lvd1689m](/model/facebook/dinov3-vitl16-pretrain-lvd1689m)
*   [facebook/dinov3-vits16-pretrain-lvd1689m](/model/facebook/dinov3-vits16-pretrain-lvd1689m)
*   [facebook/EdgeTAM](/model/facebook/EdgeTAM)
*   [facebook/encodec\_24khz](/model/facebook/encodec_24khz)
*   [facebook/encodec\_48khz](/model/facebook/encodec_48khz)
*   [facebook/faiss](/model/facebook/faiss)
*   [facebook/hubert-large-ls960-ft](/model/facebook/hubert-large-ls960-ft)
*   [facebook/meta-encoder-v1](/model/facebook/meta-encoder-v1)
*   [facebook/metaclip-2-worldwide-huge-quickgelu](/model/facebook/metaclip-2-worldwide-huge-quickgelu)
*   [facebook/mms-1b-all](/model/facebook/mms-1b-all)
*   [facebook/pe-av-large](/model/facebook/pe-av-large)
*   [facebook/PE-Core-G14-448](/model/facebook/PE-Core-G14-448)
*   [facebook/PE-Spatial-G14-448](/model/facebook/PE-Spatial-G14-448)
*   [facebook/Perception-LM-3B](/model/facebook/Perception-LM-3B)
*   [facebook/sam-vit-huge](/model/facebook/sam-vit-huge)
*   [facebook/sam2.1-hiera-base-plus](/model/facebook/sam2.1-hiera-base-plus)
*   [facebook/sam3.1](/model/facebook/sam3.1)
*   [facebook/seamless-m4t-v2-large](/model/facebook/seamless-m4t-v2-large)
*   [facebook/VGGT-1B](/model/facebook/VGGT-1B)
*   [facebook/wav2vec2-large-960h](/model/facebook/wav2vec2-large-960h)
*   [fastino/gliner2-base-v1](/model/fastino/gliner2-base-v1)
*   [fastino/GLiNER2.5-Decide](/model/fastino/GLiNER2.5-Decide)
*   [FermionResearch/Phonon-2](/model/FermionResearch/Phonon-2)
*   [FireRedTeam/FireRed-OCR](/model/FireRedTeam/FireRed-OCR)
*   [FireRedTeam/ReMatch-3B](/model/FireRedTeam/ReMatch-3B)
*   [foduucom/table-detection-and-extraction](/model/foduucom/table-detection-and-extraction)
*   [FunAudioLLM/SenseVoiceSmall](/model/FunAudioLLM/SenseVoiceSmall)
*   [fushh7/ObjEmbed-2B](/model/fushh7/ObjEmbed-2B)
*   [google/deplot](/model/google/deplot)
*   [google/embeddinggemma-2](/model/google/embeddinggemma-2)
*   [google/embeddinggemma-300m](/model/google/embeddinggemma-300m)
*   [google/gemma-4-12B-it](/model/google/gemma-4-12B-it)
*   [google/gemma-4-26B-A4B-it](/model/google/gemma-4-26B-A4B-it)
*   [google/gemma-4-31B-it](/model/google/gemma-4-31B-it)
*   [google/gemma-4-E2B-it](/model/google/gemma-4-E2B-it)
*   [google/gemma-4-E4B-it](/model/google/gemma-4-E4B-it)
*   [google/medgemma-27b-it](/model/google/medgemma-27b-it)
*   [google/owlv2-large-patch14-ensemble](/model/google/owlv2-large-patch14-ensemble)
*   [google/owlvit-large-patch14](/model/google/owlvit-large-patch14)
*   [google/paligemma2-3b-mix-448](/model/google/paligemma2-3b-mix-448)
*   [google/pix2struct-base](/model/google/pix2struct-base)
*   [google/scann](/model/google/scann)
*   [google/timesfm-2.0-500m-pytorch](/model/google/timesfm-2.0-500m-pytorch)
*   [google/timesfm-2.5-200m-transformers](/model/google/timesfm-2.5-200m-transformers)
*   [google/tipsv2-so400m14](/model/google/tipsv2-so400m14)
*   [google/videoprism-large-f8r288](/model/google/videoprism-large-f8r288)
*   [Haon-Chen/e5-omni-7B](/model/Haon-Chen/e5-omni-7B)
*   [Hcompany/Holo-3.1-4B](/model/Hcompany/Holo-3.1-4B)
*   [Hcompany/NeoMME-800M-Retriever](/model/Hcompany/NeoMME-800M-Retriever)
*   [hindsight-ai/hs-embed-1](/model/hindsight-ai/hs-embed-1)
*   [HuggingFaceTB/SmolVLM2-2.2B-Instruct](/model/HuggingFaceTB/SmolVLM2-2.2B-Instruct)
*   [hustvl/yolos-tiny](/model/hustvl/yolos-tiny)
*   [ibm-granite/granite-4.0-1b-speech](/model/ibm-granite/granite-4.0-1b-speech)
*   [ibm-granite/granite-4.0-3b-vision](/model/ibm-granite/granite-4.0-3b-vision)
*   [ibm-granite/granite-docling-258M](/model/ibm-granite/granite-docling-258M)
*   [ibm-granite/granite-embedding-311m-multilingual-r2](/model/ibm-granite/granite-embedding-311m-multilingual-r2)
*   [ibm-granite/granite-embedding-97m-multilingual-r2](/model/ibm-granite/granite-embedding-97m-multilingual-r2)
*   [ibm-granite/granite-embedding-english-r2](/model/ibm-granite/granite-embedding-english-r2)
*   [ibm-granite/granite-embedding-reranker-english-r2](/model/ibm-granite/granite-embedding-reranker-english-r2)
*   [ibm-granite/granite-embedding-small-english-r2](/model/ibm-granite/granite-embedding-small-english-r2)
*   [ibm-granite/granite-speech-4.1-2b](/model/ibm-granite/granite-speech-4.1-2b)
*   [ibm-granite/granite-speech-4.1-2b-plus](/model/ibm-granite/granite-speech-4.1-2b-plus)
*   [ibm-granite/granite-speech-5.0-2b](/model/ibm-granite/granite-speech-5.0-2b)
*   [ibm-granite/granite-vision-4.1-4b](/model/ibm-granite/granite-vision-4.1-4b)
*   [IDEA-Research/grounding-dino-base](/model/IDEA-Research/grounding-dino-base)
*   [Idiap/EdgeFace-S-GAMMA](/model/Idiap/EdgeFace-S-GAMMA)
*   [immich-app/buffalo\_l](/model/immich-app/buffalo_l)
*   [Intel/dpt-large](/model/Intel/dpt-large)
*   [intfloat/multilingual-e5-large](/model/intfloat/multilingual-e5-large)
*   [intfloat/multilingual-e5-small](/model/intfloat/multilingual-e5-small)
*   [iSEE-Laboratory/llmdet\_large](/model/iSEE-Laboratory/llmdet_large)
*   [jinaai/jina-clip-v2](/model/jinaai/jina-clip-v2)
*   [jinaai/jina-code-embeddings-1.5b](/model/jinaai/jina-code-embeddings-1.5b)
*   [jinaai/jina-embeddings-v3](/model/jinaai/jina-embeddings-v3)
*   [jinaai/jina-embeddings-v4](/model/jinaai/jina-embeddings-v4)
*   [jinaai/jina-embeddings-v5-omni-nano](/model/jinaai/jina-embeddings-v5-omni-nano)
*   [jinaai/jina-embeddings-v5-omni-nano-retrieval](/model/jinaai/jina-embeddings-v5-omni-nano-retrieval)
*   [jinaai/jina-embeddings-v5-omni-small](/model/jinaai/jina-embeddings-v5-omni-small)
*   [jinaai/jina-embeddings-v5-omni-small-retrieval](/model/jinaai/jina-embeddings-v5-omni-small-retrieval)
*   [jinaai/jina-embeddings-v5-text-nano](/model/jinaai/jina-embeddings-v5-text-nano)
*   [jinaai/jina-embeddings-v5-text-small](/model/jinaai/jina-embeddings-v5-text-small)
*   [jinaai/jina-reranker-m0](/model/jinaai/jina-reranker-m0)
*   [jinaai/jina-reranker-v3](/model/jinaai/jina-reranker-v3)
*   [jinaai/jina-reranker-v3.5](/model/jinaai/jina-reranker-v3.5)
*   [Kingsoft-LLM/QZhou-Embedding](/model/Kingsoft-LLM/QZhou-Embedding)
*   [Kwai-Keye/Keye-VL-2.0-30B-A3B](/model/Kwai-Keye/Keye-VL-2.0-30B-A3B)
*   [Kwai-Keye/Keye-VL-8B-Preview](/model/Kwai-Keye/Keye-VL-8B-Preview)
*   [kyutai/mimi](/model/kyutai/mimi)
*   [kyutai/stt-2.6b-en](/model/kyutai/stt-2.6b-en)
*   [laion/clap-htsat-fused](/model/laion/clap-htsat-fused)
*   [laion/clap-htsat-unfused](/model/laion/clap-htsat-unfused)
*   [laion/clap2-large-audioxl-s1B](/model/laion/clap2-large-audioxl-s1B)
*   [laion/larger\_clap\_general](/model/laion/larger_clap_general)
*   [laion/larger\_clap\_music](/model/laion/larger_clap_music)
*   [laion/larger\_clap\_music\_and\_speech](/model/laion/larger_clap_music_and_speech)
*   [LCO-Embedding/LCO-Embedding-Omni-3B](/model/LCO-Embedding/LCO-Embedding-Omni-3B)
*   [LCO-Embedding/LCO-Embedding-Omni-7B](/model/LCO-Embedding/LCO-Embedding-Omni-7B)
*   [LGAI-EXAONE/EXAONE-4.5-33B](/model/LGAI-EXAONE/EXAONE-4.5-33B)
*   [lightonai/Agent-ModernColBERT](/model/lightonai/Agent-ModernColBERT)
*   [lightonai/GTE-ModernColBERT-v1](/model/lightonai/GTE-ModernColBERT-v1)
*   [lightonai/LateOn-Code](/model/lightonai/LateOn-Code)
*   [lightonai/LightOnOCR-2-1B](/model/lightonai/LightOnOCR-2-1B)
*   [lightonai/LightOnOCR-3-4B](/model/lightonai/LightOnOCR-3-4B)
*   [lightonai/Reason-ModernColBERT](/model/lightonai/Reason-ModernColBERT)
*   [lightonai/SlideOn](/model/lightonai/SlideOn)
*   [LiquidAI/d1-3B](/model/LiquidAI/d1-3B)
*   [LiquidAI/d1-omni-600M](/model/LiquidAI/d1-omni-600M)
*   [LiquidAI/LFM2.5-ColBERT-350M](/model/LiquidAI/LFM2.5-ColBERT-350M)
*   [LiquidAI/LFM3-Omni-2B](/model/LiquidAI/LFM3-Omni-2B)
*   [LiquidAI/LFM3-VL-2B](/model/LiquidAI/LFM3-VL-2B)
*   [lpiccinelli/unidepth-v2-vitl14](/model/lpiccinelli/unidepth-v2-vitl14)
*   [m-a-p/MERT-v1-330M](/model/m-a-p/MERT-v1-330M)
*   [m-a-p/MERT-v1-95M](/model/m-a-p/MERT-v1-95M)
*   [m-a-p/MERT-v2-FullSong](/model/m-a-p/MERT-v2-FullSong)
*   [Maple728/TimeMoE-50M](/model/Maple728/TimeMoE-50M)
*   [MCG-NJU/OneStreamer-4B](/model/MCG-NJU/OneStreamer-4B)
*   [MCG-NJU/TimeLens2-8B](/model/MCG-NJU/TimeLens2-8B)
*   [meta-models/Muse-Spark-Open-816B-A42B](/model/meta-models/Muse-Spark-Open-816B-A42B)
*   [meta/muse-spark](/model/meta/muse-spark)
*   [microsoft/BEATs](/model/microsoft/BEATs)
*   [microsoft/codebert-base](/model/microsoft/codebert-base)
*   [microsoft/dit-large](/model/microsoft/dit-large)
*   [microsoft/Fara-7B](/model/microsoft/Fara-7B)
*   [microsoft/Florence-2-large](/model/microsoft/Florence-2-large)
*   [microsoft/harrier-oss-v1-0.6b](/model/microsoft/harrier-oss-v1-0.6b)
*   [microsoft/layoutlmv3-base](/model/microsoft/layoutlmv3-base)
*   [microsoft/Mage-VL](/model/microsoft/Mage-VL)
*   [microsoft/OmniParser-v2.0](/model/microsoft/OmniParser-v2.0)
*   [microsoft/Phi-4-multimodal-instruct](/model/microsoft/Phi-4-multimodal-instruct)
*   [microsoft/Phi-4-reasoning-vision-15B](/model/microsoft/Phi-4-reasoning-vision-15B)
*   [microsoft/table-transformer-detection](/model/microsoft/table-transformer-detection)
*   [microsoft/table-transformer-structure-recognition](/model/microsoft/table-transformer-structure-recognition)
*   [microsoft/table-transformer-structure-recognition-v1.1-all](/model/microsoft/table-transformer-structure-recognition-v1.1-all)
*   [microsoft/table-transformer-structure-recognition-v1.1-pub](/model/microsoft/table-transformer-structure-recognition-v1.1-pub)
*   [microsoft/trocr-large-handwritten](/model/microsoft/trocr-large-handwritten)
*   [microsoft/trocr-large-printed](/model/microsoft/trocr-large-printed)
*   [microsoft/VibeVoice-ASR](/model/microsoft/VibeVoice-ASR)
*   [microsoft/VibeVoice-ASR-HF](/model/microsoft/VibeVoice-ASR-HF)
*   [microsoft/wavlm-large](/model/microsoft/wavlm-large)
*   [minchul/cvlface\_adaface\_ir101\_webface12m](/model/minchul/cvlface_adaface_ir101_webface12m)
*   [minchul/cvlface\_adaface\_ir50\_ms1mv2](/model/minchul/cvlface_adaface_ir50_ms1mv2)
*   [minchul/cvlface\_adaface\_vit\_base\_kprpe\_webface12m](/model/minchul/cvlface_adaface_vit_base_kprpe_webface12m)
*   [minchul/cvlface\_adaface\_vit\_base\_webface4m](/model/minchul/cvlface_adaface_vit_base_webface4m)
*   [MiniMaxAI/MiniMax-M3](/model/MiniMaxAI/MiniMax-M3)
*   [minishlab/blink-8M](/model/minishlab/blink-8M)
*   [minishlab/blink-multilingual-64M](/model/minishlab/blink-multilingual-64M)
*   [mispeech/dasheng-1.2B](/model/mispeech/dasheng-1.2B)
*   [mistralai/Mistral-Large-4-1T-A52B](/model/mistralai/Mistral-Large-4-1T-A52B)
*   [mistralai/Voxtral-Mini-3B-2507](/model/mistralai/Voxtral-Mini-3B-2507)
*   [mistralai/Voxtral-Mini-4B-Realtime-2602](/model/mistralai/Voxtral-Mini-4B-Realtime-2602)
*   [mistralai/Voxtral-Mini-4B-Realtime-Arabic](/model/mistralai/Voxtral-Mini-4B-Realtime-Arabic)
*   [MIT/ast-finetuned-audioset-10-10-0.4593](/model/MIT/ast-finetuned-audioset-10-10-0.4593)
*   [mixedbread-ai/mxbai-colbert-large-v1](/model/mixedbread-ai/mxbai-colbert-large-v1)
*   [mixedbread-ai/mxbai-embed-large-v1](/model/mixedbread-ai/mxbai-embed-large-v1)
*   [mixedbread-ai/mxbai-rerank-large-v2](/model/mixedbread-ai/mxbai-rerank-large-v2)
*   [ModernVBERT/ColModernVBERT](/model/ModernVBERT/ColModernVBERT)
*   [Modotte/AIRealNet-Audio](/model/Modotte/AIRealNet-Audio)
*   [moondream/moondream3-preview](/model/moondream/moondream3-preview)
*   [moondream/parakeet-redux](/model/moondream/parakeet-redux)
*   [moondream/parakeet-ultra](/model/moondream/parakeet-ultra)
*   [moonshotai/Kimi-K2.6](/model/moonshotai/Kimi-K2.6)
*   [moonshotai/Kimi-K3.1-Pro](/model/moonshotai/Kimi-K3.1-Pro)
*   [moonshotai/Kimi-VL-A3B-Thinking-2506](/model/moonshotai/Kimi-VL-A3B-Thinking-2506)
*   [moonshotai/MoonViT-SO-400M](/model/moonshotai/MoonViT-SO-400M)
*   [mtg-upf/discogs-maest-30s-pw-129e](/model/mtg-upf/discogs-maest-30s-pw-129e)
*   [nanonets/Nanonets-OCR2-3B](/model/nanonets/Nanonets-OCR2-3B)
*   [naver-clova-ix/donut-base](/model/naver-clova-ix/donut-base)
*   [NCSOFT/GME-VARCO-VISION-Embedding](/model/NCSOFT/GME-VARCO-VISION-Embedding)
*   [NemoStation/Marlin-2B](/model/NemoStation/Marlin-2B)
*   [netease-youdao/Confucius4-R2T2](/model/netease-youdao/Confucius4-R2T2)
*   [netflix/void-model](/model/netflix/void-model)
*   [nlpai-lab/RenderRank-2B](/model/nlpai-lab/RenderRank-2B)
*   [nomic-ai/CodeRankEmbed](/model/nomic-ai/CodeRankEmbed)
*   [nomic-ai/colnomic-embed-multimodal-7b](/model/nomic-ai/colnomic-embed-multimodal-7b)
*   [nomic-ai/modernbert-embed-base](/model/nomic-ai/modernbert-embed-base)
*   [nomic-ai/modernbert-embed-large](/model/nomic-ai/modernbert-embed-large)
*   [nomic-ai/nomic-embed-code](/model/nomic-ai/nomic-embed-code)
*   [nomic-ai/nomic-embed-multimodal-3b](/model/nomic-ai/nomic-embed-multimodal-3b)
*   [nomic-ai/nomic-embed-multimodal-7b](/model/nomic-ai/nomic-embed-multimodal-7b)
*   [nomic-ai/nomic-embed-text-v1.5](/model/nomic-ai/nomic-embed-text-v1.5)
*   [nomic-ai/nomic-embed-text-v2-moe](/model/nomic-ai/nomic-embed-text-v2-moe)
*   [nomic-ai/nomic-embed-vision-v1.5](/model/nomic-ai/nomic-embed-vision-v1.5)
*   [numind/NuExtract3](/model/numind/NuExtract3)
*   [nvidia/4D-RGPT-8B](/model/nvidia/4D-RGPT-8B)
*   [nvidia/C-RADIOv4-H](/model/nvidia/C-RADIOv4-H)
*   [nvidia/C-RADIOv4-SO400M](/model/nvidia/C-RADIOv4-SO400M)
*   [nvidia/canary-1b-v2](/model/nvidia/canary-1b-v2)
*   [nvidia/canary-qwen-2.5b](/model/nvidia/canary-qwen-2.5b)
*   [nvidia/Cosmos-Embed1-448p-anomaly-detection](/model/nvidia/Cosmos-Embed1-448p-anomaly-detection)
*   [nvidia/Cosmos-Reason2-2B](/model/nvidia/Cosmos-Reason2-2B)
*   [nvidia/Cosmos3-Nano](/model/nvidia/Cosmos3-Nano)
*   [nvidia/diar\_sortformer\_4spk-v1](/model/nvidia/diar_sortformer_4spk-v1)
*   [nvidia/diar\_streaming\_sortformer\_4spk-v2](/model/nvidia/diar_streaming_sortformer_4spk-v2)
*   [nvidia/Eagle2.5-8B](/model/nvidia/Eagle2.5-8B)
*   [nvidia/llama-embed-nemotron-8b](/model/nvidia/llama-embed-nemotron-8b)
*   [nvidia/llama-nemotron-embed-vl-1b-v2](/model/nvidia/llama-nemotron-embed-vl-1b-v2)
*   [nvidia/llama-nemotron-rerank-1b-v2](/model/nvidia/llama-nemotron-rerank-1b-v2)
*   [nvidia/llama-nemotron-rerank-vl-1b-v2](/model/nvidia/llama-nemotron-rerank-vl-1b-v2)
*   [nvidia/LocateAnything-3B](/model/nvidia/LocateAnything-3B)
*   [nvidia/Nemotron-3-Diarization](/model/nvidia/Nemotron-3-Diarization)
*   [nvidia/Nemotron-3-Embed-1B-BF16](/model/nvidia/Nemotron-3-Embed-1B-BF16)
*   [nvidia/Nemotron-3-Embed-8B-BF16](/model/nvidia/Nemotron-3-Embed-8B-BF16)
*   [nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16](/model/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16)
*   [nvidia/nemotron-3.5-asr-streaming-0.6b](/model/nvidia/nemotron-3.5-asr-streaming-0.6b)
*   [nvidia/Nemotron-3.5-Embed-1B-BF16](/model/nvidia/Nemotron-3.5-Embed-1B-BF16)
*   [nvidia/Nemotron-3.5-Embed-8B-BF16](/model/nvidia/Nemotron-3.5-Embed-8B-BF16)
*   [nvidia/Nemotron-3.5-Rerank-8B-BF16](/model/nvidia/Nemotron-3.5-Rerank-8B-BF16)
*   [nvidia/nemotron-colembed-vl-8b-v2](/model/nvidia/nemotron-colembed-vl-8b-v2)
*   [nvidia/nemotron-ocr-v2](/model/nvidia/nemotron-ocr-v2)
*   [nvidia/nemotron-page-elements-v3](/model/nvidia/nemotron-page-elements-v3)
*   [nvidia/nemotron-speech-streaming-en-0.6b](/model/nvidia/nemotron-speech-streaming-en-0.6b)
*   [nvidia/NV-Embed-v2](/model/nvidia/NV-Embed-v2)
*   [nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B](/model/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B)
*   [nvidia/NVIDIA-Nemotron-Parse-v1.1](/model/nvidia/NVIDIA-Nemotron-Parse-v1.1)
*   [nvidia/omni-embed-nemotron-3b](/model/nvidia/omni-embed-nemotron-3b)
*   [nvidia/parakeet-ctc-1.1b](/model/nvidia/parakeet-ctc-1.1b)
*   [nvidia/parakeet-rnnt-1.1b](/model/nvidia/parakeet-rnnt-1.1b)
*   [nvidia/parakeet-tdt-0.6b-v3](/model/nvidia/parakeet-tdt-0.6b-v3)
*   [nvidia/parakeet-tdt-1.1b](/model/nvidia/parakeet-tdt-1.1b)
*   [nvidia/speakerverification\_en\_titanet\_large](/model/nvidia/speakerverification_en_titanet_large)
*   [Octen/Octen-Embedding-8B](/model/Octen/Octen-Embedding-8B)
*   [omlab/omdet-turbo-swin-tiny-hf](/model/omlab/omdet-turbo-swin-tiny-hf)
*   [omni-research/Tarsier2-7b-0115](/model/omni-research/Tarsier2-7b-0115)
*   [openai/whisper-large-v3](/model/openai/whisper-large-v3)
*   [openbmb/MiniCPM-o-4\_5](/model/openbmb/MiniCPM-o-4_5)
*   [openbmb/MiniCPM-OCR-1.0](/model/openbmb/MiniCPM-OCR-1.0)
*   [openbmb/MiniCPM-V-4\_5](/model/openbmb/MiniCPM-V-4_5)
*   [openbmb/MiniCPM-V-4.6](/model/openbmb/MiniCPM-V-4.6)
*   [openbmb/MiniCPM-V-4.7-1B](/model/openbmb/MiniCPM-V-4.7-1B)
*   [openbmb/MiniCPM-V-4.7-35B-A3B](/model/openbmb/MiniCPM-V-4.7-35B-A3B)
*   [openbmb/Trident-Qwen3VL-2B](/model/openbmb/Trident-Qwen3VL-2B)
*   [opendatalab/MinerU2.5-Pro-2604-1.2B](/model/opendatalab/MinerU2.5-Pro-2604-1.2B)
*   [OpenGVLab/InternVideo2-Stage1-1B-224p-K700](/model/OpenGVLab/InternVideo2-Stage1-1B-224p-K700)
*   [OpenGVLab/InternVL3\_5-8B](/model/OpenGVLab/InternVL3_5-8B)
*   [OpenGVLab/InternVL3-78B](/model/OpenGVLab/InternVL3-78B)
*   [OpenGVLab/InternVL3-8B](/model/OpenGVLab/InternVL3-8B)
*   [openmmlab-community/mm\_grounding\_dino\_large\_all](/model/openmmlab-community/mm_grounding_dino_large_all)
*   [opensearch-project/opensearch-neural-embed-v1](/model/opensearch-project/opensearch-neural-embed-v1)
*   [PaddlePaddle/paddleocr](/model/PaddlePaddle/paddleocr)
*   [PaddlePaddle/PaddleOCR-VL-1.5](/model/PaddlePaddle/PaddleOCR-VL-1.5)
*   [PaddlePaddle/PaddleOCR-VL-1.6](/model/PaddlePaddle/PaddleOCR-VL-1.6)
*   [PaddlePaddle/PP-DocLayoutV3](/model/PaddlePaddle/PP-DocLayoutV3)
*   [ParaVT/ParaVT-8B](/model/ParaVT/ParaVT-8B)
*   [PekingU/rtdetr\_v2\_r101vd](/model/PekingU/rtdetr_v2_r101vd)
*   [PekingU/rtdetr\_v2\_r18vd](/model/PekingU/rtdetr_v2_r18vd)
*   [perplexity-ai/pplx-embed-context-v1-4b](/model/perplexity-ai/pplx-embed-context-v1-4b)
*   [perplexity-ai/pplx-embed-v1-0.6b](/model/perplexity-ai/pplx-embed-v1-0.6b)
*   [perplexity-ai/pplx-embed-v1-late-0.6b](/model/perplexity-ai/pplx-embed-v1-late-0.6b)
*   [perplexity-ai/pplx-embed-v2-context-0.6b](/model/perplexity-ai/pplx-embed-v2-context-0.6b)
*   [perplexity-ai/pplx-embed-v2-context-9b](/model/perplexity-ai/pplx-embed-v2-context-9b)
*   [perplexity-ai/pplx-embed-v2-context-9b-preview](/model/perplexity-ai/pplx-embed-v2-context-9b-preview)
*   [perplexity-ai/pplx-embed-v2-late-0.6b](/model/perplexity-ai/pplx-embed-v2-late-0.6b)
*   [perplexity-ai/pplx-embed-v2-late-9b](/model/perplexity-ai/pplx-embed-v2-late-9b)
*   [poloclub/UniTable](/model/poloclub/UniTable)
*   [pyannote/speaker-diarization-3.1](/model/pyannote/speaker-diarization-3.1)
*   [pyannote/speaker-diarization-community-1](/model/pyannote/speaker-diarization-community-1)
*   [pyannote/wespeaker-voxceleb-resnet34-LM](/model/pyannote/wespeaker-voxceleb-resnet34-LM)
*   [Qwen/Qwen3-ASR-0.6B](/model/Qwen/Qwen3-ASR-0.6B)
*   [Qwen/Qwen3-ASR-0.6B-hf](/model/Qwen/Qwen3-ASR-0.6B-hf)
*   [Qwen/Qwen3-ASR-1.7B](/model/Qwen/Qwen3-ASR-1.7B)
*   [Qwen/Qwen3-Embedding-4B](/model/Qwen/Qwen3-Embedding-4B)
*   [Qwen/Qwen3-Embedding-8B](/model/Qwen/Qwen3-Embedding-8B)
*   [Qwen/Qwen3-ForcedAligner-0.6B](/model/Qwen/Qwen3-ForcedAligner-0.6B)
*   [Qwen/Qwen3-Reranker-0.6B](/model/Qwen/Qwen3-Reranker-0.6B)
*   [Qwen/Qwen3-Reranker-4B](/model/Qwen/Qwen3-Reranker-4B)
*   [Qwen/Qwen3-Reranker-8B](/model/Qwen/Qwen3-Reranker-8B)
*   [Qwen/Qwen3-VL-30B-A3B-Instruct](/model/Qwen/Qwen3-VL-30B-A3B-Instruct)
*   [Qwen/Qwen3-VL-4B-Instruct](/model/Qwen/Qwen3-VL-4B-Instruct)
*   [Qwen/Qwen3-VL-8B-Instruct](/model/Qwen/Qwen3-VL-8B-Instruct)
*   [Qwen/Qwen3-VL-Embedding-2B](/model/Qwen/Qwen3-VL-Embedding-2B)
*   [Qwen/Qwen3-VL-Embedding-8B](/model/Qwen/Qwen3-VL-Embedding-8B)
*   [Qwen/Qwen3-VL-Reranker-2B](/model/Qwen/Qwen3-VL-Reranker-2B)
*   [Qwen/Qwen3-VL-Reranker-8B](/model/Qwen/Qwen3-VL-Reranker-8B)
*   [Qwen/Qwen3.6-27B](/model/Qwen/Qwen3.6-27B)
*   [Qwen/Qwen3.6-35B-A3B](/model/Qwen/Qwen3.6-35B-A3B)
*   [Qwen/Qwen3.8-27B](/model/Qwen/Qwen3.8-27B)
*   [Qwen/Qwen3.8-Flash-Next](/model/Qwen/Qwen3.8-Flash-Next)
*   [rednote-hilab/dots.ocr](/model/rednote-hilab/dots.ocr)
*   [reducto/RolmOCR](/model/reducto/RolmOCR)
*   [Roboflow/rf-detr-large](/model/Roboflow/rf-detr-large)
*   [Roboflow/rf-detr-medium](/model/Roboflow/rf-detr-medium)
*   [Roboflow/rf-detr-seg-large](/model/Roboflow/rf-detr-seg-large)
*   [salesforce-sovereign-intelligence/SOV-Transcribe-1](/model/salesforce-sovereign-intelligence/SOV-Transcribe-1)
*   [Salesforce/blip2-opt-2.7b](/model/Salesforce/blip2-opt-2.7b)
*   [Salesforce/codet5p-110m-embedding](/model/Salesforce/codet5p-110m-embedding)
*   [Salesforce/moirai-2.0-R-small](/model/Salesforce/moirai-2.0-R-small)
*   [Salesforce/SFR-Embedding-Code-2B\_R](/model/Salesforce/SFR-Embedding-Code-2B_R)
*   [Salesforce/SFR-Embedding-Code-400M\_R](/model/Salesforce/SFR-Embedding-Code-400M_R)
*   [sensenova/SenseNova-U1-8B-MoT](/model/sensenova/SenseNova-U1-8B-MoT)
*   [sentence-transformers/all-MiniLM-L12-v2](/model/sentence-transformers/all-MiniLM-L12-v2)
*   [sentence-transformers/all-mpnet-base-v2](/model/sentence-transformers/all-mpnet-base-v2)
*   [sentence-transformers/LaBSE](/model/sentence-transformers/LaBSE)
*   [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](/model/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
*   [Snowflake/snowflake-arctic-embed-l-v2.0](/model/Snowflake/snowflake-arctic-embed-l-v2.0)
*   [Snowflake/snowflake-arctic-embed-m-v2.0](/model/Snowflake/snowflake-arctic-embed-m-v2.0)
*   [speechbrain/spkrec-ecapa-voxceleb](/model/speechbrain/spkrec-ecapa-voxceleb)
*   [StarDoc-AI/TeleOCR](/model/StarDoc-AI/TeleOCR)
*   [stepfun-ai/GOT-OCR-2.0-hf](/model/stepfun-ai/GOT-OCR-2.0-hf)
*   [stepfun-ai/Step-3.7-Flash](/model/stepfun-ai/Step-3.7-Flash)
*   [Systran/faster-whisper-large-v3](/model/Systran/faster-whisper-large-v3)
*   [tencent/EVIE-4.5B](/model/tencent/EVIE-4.5B)
*   [tencent/EVIE-8B](/model/tencent/EVIE-8B)
*   [tencent/HunyuanOCR](/model/tencent/HunyuanOCR)
*   [tencent/Hy4-flash](/model/tencent/Hy4-flash)
*   [tencent/WeMM-Embedding-2B](/model/tencent/WeMM-Embedding-2B)
*   [tencent/WeMM-Embedding-4B](/model/tencent/WeMM-Embedding-4B)
*   [tencent/WeMM-Embedding-9B](/model/tencent/WeMM-Embedding-9B)
*   [tencent/WeMM-Video-35BA3B](/model/tencent/WeMM-Video-35BA3B)
*   [tencent/Youtu-Parsing-Omni](/model/tencent/Youtu-Parsing-Omni)
*   [TencentARC/TimeLens-8B](/model/TencentARC/TimeLens-8B)
*   [thebajajra/RexReranker-base](/model/thebajajra/RexReranker-base)
*   [thebajajra/RexReranker-large](/model/thebajajra/RexReranker-large)
*   [thinkingmachines/Inkling-2-Mini](/model/thinkingmachines/Inkling-2-Mini)
*   [thinkingmachines/Inkling-2-Small](/model/thinkingmachines/Inkling-2-Small)
*   [tiiuae/Falcon-OCR](/model/tiiuae/Falcon-OCR)
*   [timesler/facenet-pytorch](/model/timesler/facenet-pytorch)
*   [TomoroAI/tomoro-colqwen3-embed-4b](/model/TomoroAI/tomoro-colqwen3-embed-4b)
*   [tsinghua-ee/WAVE-7B](/model/tsinghua-ee/WAVE-7B)
*   [ultralytics/yolo11n](/model/ultralytics/yolo11n)
*   [ultralytics/yolo26n](/model/ultralytics/yolo26n)
*   [ultralytics/yolov8n](/model/ultralytics/yolov8n)
*   [usefulsensors/moonshine-streaming-medium](/model/usefulsensors/moonshine-streaming-medium)
*   [ustc-community/dfine-xlarge-coco](/model/ustc-community/dfine-xlarge-coco)
*   [vidore/colpali-v1.2](/model/vidore/colpali-v1.2)
*   [vidore/colpali-v1.3](/model/vidore/colpali-v1.3)
*   [vidore/colqwen-omni-v0.1](/model/vidore/colqwen-omni-v0.1)
*   [vidore/colqwen2.5-v0.2](/model/vidore/colqwen2.5-v0.2)
*   [Vision-CAIR/Tempo-6B](/model/Vision-CAIR/Tempo-6B)
*   [VLM2Vec/VLM2Vec-V2.0](/model/VLM2Vec/VLM2Vec-V2.0)
*   [voyageai/voyage-4-nano](/model/voyageai/voyage-4-nano)
*   [webAI-Official/webAI-ColVec1-4b](/model/webAI-Official/webAI-ColVec1-4b)
*   [Wespeaker/wespeaker-voxceleb-resnet293-LM](/model/Wespeaker/wespeaker-voxceleb-resnet293-LM)
*   [WorldSeek-AI/WorldSeek-Omni-2B-Preview](/model/WorldSeek-AI/WorldSeek-Omni-2B-Preview)
*   [xiaomi-research/Xiaomi-OCR-0](/model/xiaomi-research/Xiaomi-OCR-0)
*   [XiaomiMiMo/MiMo-V2.5-ASR](/model/XiaomiMiMo/MiMo-V2.5-ASR)
*   [yanziang/InternVideo3-8B-Instruct](/model/yanziang/InternVideo3-8B-Instruct)
*   [yyfz233/Pi3](/model/yyfz233/Pi3)
*   [zai-org/GLM-4.5V](/model/zai-org/GLM-4.5V)
*   [zai-org/GLM-4.6V](/model/zai-org/GLM-4.6V)
*   [zai-org/GLM-5.3-Flash](/model/zai-org/GLM-5.3-Flash)
*   [zai-org/GLM-OCR](/model/zai-org/GLM-OCR)
*   [zeroentropy/zembed-1-embedding](/model/zeroentropy/zembed-1-embedding)
*   [zeroentropy/zerank-2-reranker](/model/zeroentropy/zerank-2-reranker)
*   [ZhengPeng7/BiRefNet](/model/ZhengPeng7/BiRefNet)
*   [ZhengPeng7/BiRefNet\_HR](/model/ZhengPeng7/BiRefNet_HR)
*   [ZhuYuhan/TimeLens2-9B](/model/ZhuYuhan/TimeLens2-9B)
*   [ZhuYuhan/VideoJev-4B](/model/ZhuYuhan/VideoJev-4B)