91 models
48 of 91 models
Hardware, cost and evidence come from each record. "Unmeasured" means we have not measured it on our own image yet.
Embedding · intfloat/multilingual-e5-large-instruct
Default text vector for search over transcripts, OCR text, descriptions, documents and web pages in 100+ languages; one space for query and passage text.
Embedding · gemini-embedding-2
One vector space for video segments, images, PDFs, audio and text queries; the default for object-level multimodal extractors (multimodal_extractor v2, universal_extractor).
Embedding · sentence-transformers/all-MiniLM-L6-v2
Small, fast English sentence vectors on CPU (22M params, 384 dims) for short text, dedup and clustering.
Embedding · multimodalembedding@001
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).
Embedding · google/siglip-base-patch16-224
Text-to-image and image-to-image search over photos, products and video frames in one shared space.
Embedding · lukewys/laion_clap
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.
Embedding · facebook/dinov2-base
Image-to-image similarity on visual structure (layout, near-duplicates, the same object or scene) with no text in the loop.
Embedding · jinaai/jina-embeddings-v2-base-code
Code snippets and natural-language-to-code search across about 30 programming languages, with up to 8192-token inputs (ALiBi).
Embedding · google/siglip-so400m-patch14-384
Strongest SigLIP v1 image-text model; the vision tower behind many VLMs (PaliGemma).
Embedding · vidore/colqwen2-v1.0-merged
Text search over document page images (PDF pages, slides, infographics, tables) by late interaction, with no OCR step.
Embedding · laion/CLIP-ViT-L-14-laion2B-s32B-b82K
Image-to-image similarity from a large web-trained ViT-L/14 image tower.
Embedding · google/siglip2-so400m-patch14-384
Logos, signage, brands and venue shots in concert footage (the visual arm of an internal eval); strongest SigLIP 2 below giant.
Embedding · Qwen/Qwen3-Embedding-0.6B
Instruction-aware multilingual text vectors from a small model (0.6B, 1024 dims) on CPU; in a custom plugin it embeds Gemini tags plus the words spoken over each shot.
Embedding · patrickjohncyh/fashion-clip
Product attributes in fashion catalogs: garment type, color, pattern, material, style words.
Embedding · Marqo/marqo-fashionCLIP
Fashion product search from text or image (ViT-B/16 CLIP fine-tuned with generalized contrastive learning on product titles, categories and attributes); Marqo reports gains over FashionCLIP 2.0 on its fashion benchmarks.
Embedding · Marqo/marqo-fashionSigLIP
Fashion product search from text or image (ViT-B/16 SigLIP fine-tuned with generalized contrastive learning on product titles, categories and attributes); Marqo reports gains over FashionCLIP 2.0 on its fashion benchmarks.
Embedding · openai/clip-vit-base-patch32
General zero-shot labels and text-to-image search; the reference baseline most papers report against.
Embedding · openai/clip-vit-large-patch14
General zero-shot labels and text-to-image search; the reference baseline most papers report against.
Embedding · laion/CLIP-ViT-B-16-laion2B-s34B-b88K
Better than B/32 on fine detail at modest cost.
Embedding · laion/CLIP-ViT-B-32-laion2B-s34B-b79K
Cheapest strong CLIP for CPU bulk frame embedding.
Embedding · laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
Largest LAION CLIP; best zero-shot accuracy in the LAION family.
Embedding · laion/CLIP-ViT-H-14-laion2B-s32B-b79K
High-accuracy CLIP for offline catalogs (the text encoder family used by Stable Diffusion 2).
Embedding · google/siglip2-base-patch16-224
Drop-in upgrade over SigLIP base: multilingual text, better localization and dense features at the same 768-d.
Directory pages for 422 public models. They are not in the catalog above, and Mixpeek does not run them as listed.