THE MODEL DIRECTORY

Every listing. A closer look.

2,876 catalog records, ordered by name. Each profile has its own link and shows where the information came from. 727 repeat listings (training checkpoints, adapters, other formats and duplicate cloud entries, each shown on its main model’s page) and listings with no published task, size, or price are left out unless you search for them. Show all 3,603

Models A–Z

Page 38 of 60 · Coverage limits

LightOn · Downloadable

mSlideOn

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Oct 13, 2026339M parameters

LightOn · Downloadable

mSlideOn-SAE

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Oct 13, 2026344M parameters

BAAI · Downloadable

MTVCraft

Video generation

Generates video. Resolution, clip length, and speed depend on the version and setup.

Listed Jun 25, 2025Size not disclosed

M-A-P · Downloadable

MuPT-v1-8192-190M

Text generation

Generates text for conversations and writing.

Listed Jan 18, 2024190M parameters

M-A-P · Downloadable

MuPT-v1-8192-550M

Text generation

Generates text for conversations and writing.

Listed Jan 18, 2024550M parameters

M-A-P · Downloadable

MuPT-v1.1-505M-8192

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Listed Apr 10, 2024505M parameters

M-A-P · Downloadable

MuPT-v1.1-8192-1.07B

Text generation

Generates text for conversations and writing.

Listed Apr 10, 20241.1B parameters

M-A-P · Downloadable

MuPT-v1.1-8192-1.97B

Text generation

Generates text for conversations and writing.

Listed Apr 10, 20242B parameters

M-A-P · Downloadable

MuPT-v1.1-8192-4.23B

Text generation

Generates text for conversations and writing.

Listed Apr 10, 20244.2B parameters

Meta · Cloud API

Muse Spark 1.1

VisionVideo understandingReasoningTool use

Cloud API for vision, video understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Apr 8, 2026

Meta · Cloud API

Muse Spark 1.2

VisionVideo understandingAudio understandingReasoningTool use

Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Aug 5, 2026

Meta · Cloud API

Muse Spark 1.2 Contributor

VisionVideo understandingAudio understandingReasoningTool use

Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Aug 5, 2026

Meta · Cloud API

Muse Spark 1.3

VisionVideo understandingAudio understandingReasoningTool use

Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Sep 2, 2026

Meta · Cloud API

Muse Spark 1.3 Contributor

VisionVideo understandingAudio understandingReasoningTool use

Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Sep 2, 2026

Meta · Cloud API

Muse Wonder

VisionVideo understandingAudio understandingReasoningTool use

Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Oct 12, 2026

Meta · Downloadable

Muse-Glimmer-30B

Vision

Understands text and images and responds in text.

Listed Aug 9, 202630B parameters

Meta · Downloadable

Muse-Glimmer-30B-assistant

VisionEmbeddings

Understands text and images and responds in text.

Listed Aug 9, 202630B parameters

Meta · Downloadable

Muse-Glimmer-30B-ExecuTorch-PTE

Vision

Understands text and images and responds in text.

Listed Aug 10, 202630B parameters

Meta · Downloadable

Muse-Spark-Open-816B-A42B

Vision

Understands text and images and responds in text.

Listed Sep 15, 2026816B parameters

NVIDIA · Downloadable

Muse-Spark-Open-816B-A42B-DFlash2

Vision

Understands text and images and responds in text.

Listed Oct 16, 2026816B parameters

Microsoft · Downloadable

MuseVLA

Robotics

Hugging Face lists its task as robotics. See the model card for supported inputs and setup.

Listed Jun 1, 2026Size not disclosed

M-A-P · Downloadable

MusiLingo-long-v1

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Apr 4, 20247.1B parameters

M-A-P · Downloadable

MusiLingo-musicqa-v1

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Apr 4, 20247.1B parameters

M-A-P · Downloadable

MusiLingo-short-v1

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Apr 4, 20247.1B parameters

LightOn · Downloadable

mxbai-edge-colbert-v0-32m-onnx

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Jan 21, 202632M parameters

Google · Cloud API

Nano Banana 2

VisionVideo understandingImage generationImage editingReasoning

Cloud API for vision, video understanding, image generation, image editing, chat & writing, reasoning. Capabilities are catalog-listed, not independently scored.

Listed May 28, 2026

Google · Cloud API

Nano Banana 2 Lite

VisionImage generationImage editingReasoningTool use

Cloud API for vision, image generation, image editing, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Listed Jun 30, 2026

Google · Cloud API

Nano Banana Pro

VisionImage generationImage editingReasoning

Cloud API for vision, image generation, image editing, chat & writing, reasoning. Capabilities are catalog-listed, not independently scored.

Listed May 28, 2026

Microsoft · Downloadable

NatureLM-8x7B

Text generation

Generates text, according to its published model architecture (MixtralForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed Jun 6, 202547B parameters

Microsoft · Downloadable

NatureLM-8x7B-Inst

Text generation

Generates text, according to its published model architecture (MixtralForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed Jun 6, 202547B parameters

Baidu · Downloadable

NAVA

Video generation

Generates video. Resolution, clip length, and speed depend on the version and setup.

Listed May 29, 2026Size not disclosed

NVIDIA · Downloadable

Nemotron-3-Diarization

Capabilities unconfirmed

Hugging Face lists its task as voice activity detection. See the model card for supported inputs and setup.

Listed Sep 1, 202699M parameters

NVIDIA · Downloadable

Nemotron-3-Embed-1B

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Jul 14, 20261B parameters

NVIDIA · Downloadable

Nemotron-3-Embed-8B

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Jul 14, 20268B parameters

NVIDIA · Downloadable

Nemotron-3-Labs-Ultra-Math-RL

Text generation

Generates text for conversations and writing.

Listed Sep 2, 2026561B parameters

NVIDIA · Downloadable

Nemotron-3-Labs-Ultra-Math-SFT

Text generation

Generates text for conversations and writing.

Listed Sep 2, 2026561B parameters

NVIDIA · Downloadable

Nemotron-3-Nano-Omni-30B-A3B-Reasoning

Embeddings

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Apr 24, 202630B parameters

NVIDIA · Downloadable

Nemotron-3-Super-120B-A12B-BF16-MTPv2

Text generation

Generates text for conversations and writing.

Listed May 24, 2026120B parameters

NVIDIA · Downloadable

nemotron-3.5-asr-streaming-0.6b

TranscriptionEmbeddingsAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed May 15, 2026600M parameters

NVIDIA · Downloadable

Nemotron-3.5-Content-Safety

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Listed May 22, 20264.3B parameters

NVIDIA · Downloadable

Nemotron-3.5-Embed-1B

Embeddings

Hugging Face lists its task as visual document retrieval. See the model card for supported inputs and setup.

Listed Oct 7, 20261B parameters

NVIDIA · Downloadable

Nemotron-3.5-Embed-8B

Embeddings

Hugging Face lists its task as visual document retrieval. See the model card for supported inputs and setup.

Listed Oct 7, 20268B parameters

NVIDIA · Downloadable

Nemotron-3.5-Parse

VisionDocument reading

Understands text and images and responds in text.

Listed Sep 3, 2026631M parameters

NVIDIA · Downloadable

Nemotron-3.5-Rerank-8B

Text classificationReranking

Hugging Face lists its task as text ranking. See the model card for supported inputs and setup.

Listed Oct 15, 20268B parameters

NVIDIA · Downloadable

Nemotron-Cascade-2-30B-A3B

Text generation

Generates text for conversations and writing.

Listed Mar 18, 202630B parameters

NVIDIA · Downloadable

Nemotron-Labs-Audex-2B

Text generation

Generates text for conversations and writing.

Listed Jul 6, 20262B parameters

NVIDIA · Downloadable

Nemotron-Labs-Audex-30B-A3B

Text generation

Generates text for conversations and writing.

Listed Jul 6, 202630B parameters

NVIDIA · Downloadable

nemotron-labs-audio-visual-flamingo-hf

Video understanding

Generates text for conversations and writing.

Listed Apr 15, 20268.7B parameters

Listing dates are source catalog dates, not verified public releases. This growing library does not yet cover every released model.