AI Model Hub

Browse AI models for multimodal decomposition and recomposition pipelines — plug any model into your extractors.

13,634 models available

Get started Schedule Demo Read Documentation

Showing 7681–7704 of 13,634 models

Image Segmentation

tue-mps/eomt-dinov3-ade-semantic-large-512

605

transformers

View Details

Any To Any

KRAFTON/Raon-Speech-9B-FP8

605

transformers

View Details

Question Answering

ThorBaller/Minstral_pubmed_gguf

604

transformers

View Details

Reinforcement Learning

igpaub/ppo-CarRacing-v2

604

stable-baselines3

View Details

Reinforcement Learning

ValueFX9507/Tifa-Deepsex-14b-CoT-Q8

603

187

transformers

View Details

Zero Shot Image Classification

mradermacher/UME-R1-7B-GGUF

603

transformers

View Details

Question Answering

mradermacher/VideoThinker-R1-3B-GGUF

603

transformers

View Details

Question Answering

Omaratef3221/llama-3.1-8b-s1-full-aramed

603

View Details

Object Detection

vivekvar/helmet-v5

602

ultralytics

View Details

Image Feature Extraction

apple/aimv2-large-patch14-native

602

transformers

View Details

Image Segmentation

keremberke/yolov8s-building-segmentation

601

ultralytics

View Details

Summarization

mradermacher/DrMedra4B-abliterated-i1-GGUF

600

transformers

View Details

Object Detection

keremberke/yolov8s-valorant-detection

600

ultralytics

View Details

Image Segmentation

google/deeplabv3_mobilenet_v2_1.0_513

600

transformers

View Details

Image To Text

EasyDeL/gemma-4-E4B-it

600

easydel

View Details

Any To Any

mlx-community/gemma-4-e2b-it-mxfp8

600

mlx

View Details

Image Feature Extraction

Aratako/gemma-4-E4B-it-audio-encoder

600

transformers

View Details

Robotics

lerobot/smolvla_robocasa

600

lerobot

View Details

Robotics

nvidia/GR00T-N1.6-BEHAVIOR1k

598

View Details

Any To Any

medoomem/gemma-4-E4B-it-The-DECKARD-V3-Expresso-HERETIC-UNCENSORED-Thinking-Q4_K_M-GGUF

598

transformers

View Details

Audio To Audio

slprl/SIMS-Llama3.2-3B

597

transformers

View Details

Image Segmentation

onnx-community/BiRefNet-ONNX

596

transformers.js

View Details

Audio Classification

superb/hubert-base-superb-ks

596

transformers

View Details

Audio Classification

Aynursusuz/whisper-large-v3-music-detection-optimized

596

transformers

View Details

......

321 / 569

Connectors

Retrievers

What's new in models

Full changelog

Jun 22, 2026200+ model pages and new retrieval deep-divesExpanded the model catalog with enriched pages (architecture, benchmarks, Mixpeek SDK examples, and pipeline pairings) across embedding, vision-language, video, audio, OCR, and reranking models — plus new vendor-neutral guides on Matryoshka embeddings, reasoning rerankers, and retrieval feedback loops.