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 7153–7176 of 13,634 models

Feature Extraction

BASF-AI/ChEmbed-prog

transformers

View Details

Tabular Classification

YuchenShen/FoMo-0D

View Details

Text To Video

samuelchristlie/Wan2.1-VACE-1.3B-GGUF

998

diffusers

View Details

Text To Audio

mispeech/Dasheng-AudioGen

998

transformers

View Details

Table Question Answering

google/tapas-small-finetuned-wtq

997

transformers

View Details

Any To Any

mlx-community/gemma-4-12B-mxfp8

996

mlx

View Details

Feature Extraction

ddidacus/smolgen-pubchem-135M-base-BPE

995

transformers

View Details

Image Feature Extraction

apple/aimv2-large-patch14-224

994

transformers

View Details

Feature Extraction

zenlm/zen-embedding-0.6B-GGUF

993

llama.cpp

View Details

Summarization

hossboll/clinical-t5

991

transformers

View Details

Text To Audio

riffusion/riffusion-model-v1

991

650

diffusers

View Details

Feature Extraction

mogam-ai/Ab-RoBERTa

991

transformers

View Details

Image Feature Extraction

ArthurZ/Ilama-3.2-1B

989

transformers

View Details

Image Segmentation

nvidia/segformer-b0-finetuned-cityscapes-640-1280

988

transformers

View Details

Any To Any

ArthurTravers/CivitAI-loras

988

diffusers

View Details

Any To Any

OsaurusAI/gemma-4-E4B-it-4bit

988

mlx

View Details

Any To Any

zecanard/gemma-4-E4B-it-ultra-uncensored-heretic-MLX-8bit-int8-affine

988

mlx

View Details

Text To Video

alibaba-pai/Wan2.1-Fun-1.3B-Control

987

113

videox_fun

View Details

Question Answering

shaina/covid_qa_distillBert

986

transformers

View Details

Summarization

csebuetnlp/mT5_m2o_arabic_crossSum

985

transformers

View Details

Image To Text

noctrex/LightOnOCR-2-1B-GGUF

985

View Details

Text To Video

Searchium-ai/clip4clip-webvid150k

985

transformers

View Details

Reinforcement Learning

sb3/sac-BipedalWalker-v3

985

stable-baselines3

View Details

Image Feature Extraction

emarro/test-hnet-upload-sweep_N_pcad2_8k_hnet_m3t1-M15-m4_N2_D1024-1024_lr-0.0005

983

transformers

View Details

......

299 / 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.