NEWMVS for embeddings. Managed for files. Both on object storage.Vectors or files. Pick a path.Start →

Start here

Vector Store (MVS)

Bring your own vectors. Dense, sparse, and BM25 search on object storage.

Managed Indexing

Connect a bucket and auto-extract scenes, faces, OCR, transcripts, and embeddings.

Build

Compose multi-stage search in <100ms: filter, join, rerank.

Feature Extractors

Typed pipelines for faces, scenes, transcripts, OCR, fingerprints.

S3, GCS, R2, Mux, LangChain, MCP, and more. Connect your stack.

Generate and store embeddings from 50+ models, then search them.

By Industry

Talent search, brand safety, creative analytics.

Scene search, recommendation, archive access.

Visual search, PDP enrichment, catalog QA.

Lecture search, transcript Q&A, content safety.

View all solutions →

By Use Case

Face & Person Search

Find anyone across video libraries in milliseconds.

IP & Copyright Detection

Logos, songs, faces: one pipeline, one report.

Visual Taste & Recs

Scene-similarity ranked recommendations with RL.

Brand & Ad Safety

Pre-publish content screening at bid-time speeds.

View all use cases →

Build

API reference, SDKs, recipes, and architecture guides.

Launches, deep dives, and field notes from our engineers.

Browse supported HuggingFace models by task and modality.

See what teams are building with Mixpeek.

Education

Multimodal University

Fundamentals of multimodal retrieval, modules + certs.

Every term you need: embeddings to re-rankers.

Talks, demos, and customer sessions on demand.

Mixpeek vs. Pinecone, Weaviate, Twelve Labs, more.

Mission, team, and the multimodal vision.

We're hiring across research, infra, and design.

Talk to sales, support, or press.

White-glove 30-day production pilot for new customers.

Sign in Request Demo Start free →

Any To Any Models

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

328 models available

Schedule Demo Read Documentation

Showing 25–48 of 328 models

Any To Any

deepseek-community/Janus-Pro-1B

131K

14

transformers

Any To Any

google/gemma-4-E4B-it-assistant

108K

105

transformers

Any To Any

llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF

100K

106

transformers

Any To Any

google/gemma-4-12B

100K

417

transformers

Any To Any

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8

91K

50

transformers

Any To Any

cyankiwi/gemma-4-12B-it-AWQ-INT4

90K

2

transformers

Any To Any

unsloth/gemma-4-12B-it-qat-GGUF

86K

125

transformers

Any To Any

google/gemma-4-12B-it-qat-w4a16-ct

77K

16

transformers

Any To Any

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

74K

17

mlx

Any To Any

openbmb/MiniCPM-o-4_5-awq

63K

20

transformers

Any To Any

cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit

59K

50

transformers

Any To Any

XiaomiMiMo/MiMo-Audio-7B-Instruct

58K

156

Any To Any

lmstudio-community/gemma-4-E2B-it-MLX-4bit

57K

transformers

Any To Any

huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated

52K

41

transformers

Any To Any

lmstudio-community/gemma-4-E2B-it-MLX-8bit

50K

transformers

Any To Any

lmstudio-community/gemma-4-E2B-it-MLX-6bit

48K

transformers

Any To Any

lmstudio-community/gemma-4-E2B-it-MLX-5bit

48K

transformers

Any To Any

mlx-community/gemma-4-e4b-it-4bit

43K

28

mlx

Any To Any

onnx-community/gemma-4-E2B-it-ONNX

43K

35

transformers.js

Any To Any

sensenova/SenseNova-U1-8B-MoT

34K

281

transformers

Any To Any

google/gemma-4-E2B-it-assistant

30K

60

transformers

Any To Any

openbmb/MiniCPM-o-4_5-gguf

29K

140

transformers

Any To Any

google/gemma-4-12B-it-qat-q4_0-gguf

25K

79

transformers

Any To Any

unsloth/gemma-4-E4B-it-qat-GGUF

23K

36

transformers

...

2 / 14

Previous

Connectors

Next

Retrievers