THE MODEL DIRECTORY

Every listing. A closer look.

All 3,562 catalog records, ordered by name, including 717 repeat checkpoints and listings whose source publishes no task, size, or price. Show described listings only

Models A–Z

Page 74 of 75 · Coverage limits

Tencent · Downloadable

WeVisOne-VL-2B

VisionDocument readingObject detection

Understands text and images and responds in text.

Listed 2B parameters

Tencent · Downloadable

WeVisOne-VL-4B

VisionDocument readingObject detection

Understands text and images and responds in text.

Listed 4B parameters

Microsoft · Downloadable

wham

Capabilities unconfirmed

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

Listed Size not disclosed

OpenAI · Downloadable

whisper-base

TranscriptionAudio understanding

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

Listed 73M parameters

OpenAI · Downloadable

whisper-base.en

TranscriptionAudio understanding

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

Listed 73M parameters

OpenAI · Downloadable

whisper-large

TranscriptionAudio understanding

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

Listed 1.5B parameters

OpenAI · Downloadable

whisper-large-v2

TranscriptionAudio understanding

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

Listed 1.5B parameters

OpenAI · Downloadable

whisper-large-v3

TranscriptionAudio understanding

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

Listed 1.5B parameters

OpenAI · Downloadable

whisper-large-v3-turbo

TranscriptionAudio understanding

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

Listed 809M parameters

OpenAI · Downloadable

whisper-medium

TranscriptionAudio understanding

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

Listed 764M parameters

OpenAI · Downloadable

whisper-medium.en

TranscriptionAudio understanding

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

Listed 764M parameters

OpenAI · Downloadable

whisper-small

TranscriptionAudio understanding

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

Listed 242M parameters

OpenAI · Downloadable

whisper-small.en

TranscriptionAudio understanding

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

Listed 242M parameters

OpenAI · Downloadable

whisper-tiny

TranscriptionAudio understanding

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

Listed 38M parameters

OpenAI · Downloadable

whisper-tiny.en

TranscriptionAudio understanding

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

Listed 38M parameters

Qwen · Alibaba · Downloadable

WorldPM-72B

Text classificationEmbeddings

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

Listed 72B parameters

Qwen · Alibaba · Downloadable

WorldPM-72B-HelpSteer2

Text classificationEmbeddings

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

Listed 72B parameters

Qwen · Alibaba · Downloadable

WorldPM-72B-RLHFLow

Text classificationEmbeddings

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

Listed 72B parameters

Qwen · Alibaba · Downloadable

WorldPM-72B-UltraFeedback

Text classificationEmbeddings

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

Listed 72B parameters

Meta · Downloadable

wt-asbs

Capabilities unconfirmed

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

Listed Size not disclosed

Microsoft · Downloadable

X-Reasoner-7B

VisionReasoning

Understands text and images and responds in text. Supports a reasoning mode.

Listed 7B parameters

M-A-P · Downloadable

xcodec

Capabilities unconfirmed

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

Listed Size not disclosed

M-A-P · Downloadable

xcodec_mini_infer

Capabilities unconfirmed

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

Listed Size not disclosed

NVIDIA · Downloadable

xmgn_drivaerml_surface

Capabilities unconfirmed

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

Listed Size not disclosed

OpenMOSS · Downloadable

XY_Tokenizer_TTSD_V0

Capabilities unconfirmed

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

Listed Size not disclosed

OpenMOSS · Downloadable

XY_Tokenizer_TTSD_V0_32k

Capabilities unconfirmed

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

Listed Size not disclosed

OpenMOSS · Downloadable

XY_Tokenizer_TTSD_V0_32k_hf

Capabilities unconfirmed

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

Listed Size not disclosed

OpenMOSS · Downloadable

XY_Tokenizer_TTSD_V0_hf

Capabilities unconfirmed

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

Listed Size not disclosed

Tencent · Downloadable

Youtu-Embedding

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed 2.4B parameters

Tencent · Downloadable

Youtu-HiChunk

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed 4.1B parameters

Tencent · Downloadable

Youtu-LLM-2B

Text generation

Generates text for conversations and writing.

Listed 2B parameters

Tencent · Downloadable

Youtu-LLM-2B-Base

Text generation

Generates text for conversations and writing.

Listed 2B parameters

Tencent · Downloadable

Youtu-LLM-A7B-Base

Vision

Understands text and images and responds in text.

Listed 118B parameters

Tencent · Downloadable

Youtu-Parsing

Vision

Understands text and images and responds in text.

Listed 2.5B parameters

Tencent · Downloadable

Youtu-Parsing-Omni

VisionDocument reading

Understands text and images and responds in text.

Listed 5.3B parameters

Tencent · Downloadable

Youtu-VL-4B-Instruct

Vision

Understands text and images and responds in text.

Listed 4B parameters

M-A-P · Downloadable

YuE-s1-0.5B

Text generation

Generates text for conversations and writing.

Listed 500M parameters

M-A-P · Downloadable

YuE-s1-7B-anneal-en-cot

Text generation

Generates text for conversations and writing.

Listed 7B parameters

M-A-P · Downloadable

YuE-s1-7B-anneal-en-icl

Text generation

Generates text for conversations and writing.

Listed 7B parameters

M-A-P · Downloadable

YuE-s1-7B-anneal-zh-cot

Text generation

Generates text for conversations and writing.

Listed 7B parameters

M-A-P · Downloadable

YuE-s1-7B-anneal-zh-icl

Text generation

Generates text for conversations and writing.

Listed 7B parameters

M-A-P · Downloadable

YuE-s2-1B-general

Text generation

Generates text for conversations and writing.

Listed 1B parameters

M-A-P · Downloadable

YuE-upsampler

Text generation

Generates text for conversations and writing.

Listed Size not disclosed

M-A-P · Downloadable

YuE2-3B

Audio generation

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

Listed 3B parameters

M-A-P · Downloadable

YuE2-Vae

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed 133M parameters

M-A-P · Downloadable

YuE2-Vae-legacy

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed 133M parameters

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