THE MODEL DIRECTORY

Every listing. A closer look.

All 3,557 catalog records, ordered by name, including 716 repeat checkpoints and listings whose source publishes no task, size, or price. Show described listings only

Models A–Z

Page 67 of 75 · Coverage limits

StepFun · Downloadable

Step-Audio-EditX-AWQ-4bit

Text generation

Generates text, according to its published model architecture (Step1ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 3.5B parameters

StepFun · Downloadable

Step-Audio-R1

Capabilities unconfirmed

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

Listed 33B parameters

StepFun · Downloadable

Step-Audio-R1.1

Capabilities unconfirmed

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

Listed 33B parameters

StepFun · Downloadable

Step-Audio-Tokenizer

Capabilities unconfirmed

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

Listed Size not disclosed

StepFun · Downloadable

Step-Audio-TTS-3B

Audio generation

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

Listed 3B parameters

StepFun · Downloadable

Step1X-3D

Capabilities unconfirmed

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

Listed Size not disclosed

StepFun · Downloadable

Step1X-Edit

Image generationImage editing

Creates or edits images. Check the model card for supported inputs and output settings.

Listed Size not disclosed

StepFun · Downloadable

Step1X-Edit-v1p1-diffusers

Image generationImage editing

Creates or edits images. Check the model card for supported inputs and output settings.

Listed 12B parameters

StepFun · Downloadable

Step1X-Edit-v1p2

Image generationImage editing

Creates or edits images. Check the model card for supported inputs and output settings.

Listed 12B parameters

StepFun · Downloadable

Step1X-Edit-v1p2-preview

Image generationImage editing

Creates or edits images. Check the model card for supported inputs and output settings.

Listed 12B parameters

StepFun · Downloadable

step3

Vision

Understands text and images and responds in text.

Listed 321B parameters

StepFun · Downloadable

Step3-VL-10B

Vision

Understands text and images and responds in text.

Listed 10B parameters

StepFun · Downloadable

Step3-VL-10B-Base

Vision

Understands text and images and responds in text.

Listed 10B parameters

StepFun · Downloadable

StepFun-Formalizer-32B

Text generation

Generates text for conversations and writing.

Listed 32B parameters

StepFun · Downloadable

StepFun-Formalizer-7B

Text generation

Generates text for conversations and writing.

Listed 7B parameters

StepFun · Downloadable

stepvideo-t2v

Video generation

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

Listed 29B parameters

StepFun · Downloadable

stepvideo-t2v-turbo

Capabilities unconfirmed

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

Listed 29B parameters

StepFun · Downloadable

stepvideo-ti2v

Video generation

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

Listed 29B parameters

NVIDIA · Downloadable

stormcast-conus

Capabilities unconfirmed

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

Listed Size not disclosed

NVIDIA · Downloadable

stormscope-meteosat

Capabilities unconfirmed

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

Listed Size not disclosed

NVIDIA · Downloadable

StormScope-NSRDB

Capabilities unconfirmed

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

Listed Size not disclosed

Kyutai · Downloadable

stt-1b-en_fr

TranscriptionAudio understanding

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

Listed 1B parameters

Kyutai · Downloadable

stt-1b-en_fr-candle

TranscriptionAudio understanding

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

Listed 1B parameters

Kyutai · Downloadable

stt-1b-en_fr-trfs

TranscriptionAudio understanding

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

Listed 1B parameters

Kyutai · Downloadable

stt-2.6b-en

TranscriptionAudio understanding

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

Listed 2.6B parameters

Kyutai · Downloadable

stt-2.6b-en-candle

TranscriptionAudio understanding

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

Listed 2.6B parameters

Kyutai · Downloadable

stt-2.6b-en-trfs

TranscriptionAudio understanding

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

Listed 2.6B parameters

Supertone · Downloadable

supertonic

Audio generation

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

Listed Size not disclosed

Supertone · Downloadable

supertonic-2

Audio generation

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

Listed Size not disclosed

Supertone · Downloadable

supertonic-3

Audio generation

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

Listed Size not disclosed

Datalab · Downloadable

surya_layout

Capabilities unconfirmed

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

Listed 126M parameters

Datalab · Downloadable

surya_layout0

Capabilities unconfirmed

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

Listed 239M parameters

Datalab · Downloadable

surya_layout2

VisionDocument readingObject detection

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

Listed Size not disclosed

Datalab · Downloadable

surya_tablerec

Capabilities unconfirmed

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

Listed 105M parameters

Datalab · Downloadable

surya-alpha

Capabilities unconfirmed

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

Listed 695M parameters

Datalab · Downloadable

surya-ocr-2

VisionDocument reading

Understands text and images and responds in text.

Listed 686M parameters

Datalab · Downloadable

surya-parsebench-rl

VisionDocument reading

Understands text and images and responds in text.

Listed 666M parameters

Stability AI · Downloadable

sv3d

Video generation

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

Listed Size not disclosed

Stability AI · Downloadable

sv4d

Capabilities unconfirmed

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

Listed Size not disclosed

Stability AI · Downloadable

sv4d2.0

Capabilities unconfirmed

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

Listed Size not disclosed

Google · Downloadable

svq

Capabilities unconfirmed

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

Listed Size not disclosed

Z.ai · Downloadable

SWE-Dev-32B

Text generation

Generates text for conversations and writing.

Listed 32B parameters

Z.ai · Downloadable

SWE-Dev-7B

Text generation

Generates text, according to its published model architecture (Qwen2ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed 7B parameters

Z.ai · Downloadable

SWE-Dev-9B

Capabilities unconfirmed

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

Listed 9B parameters

MiniMax · Downloadable

SynLogic-32B

Text generation

Generates text for conversations and writing.

Listed 32B parameters

MiniMax · Downloadable

SynLogic-7B

Text generation

Generates text for conversations and writing.

Listed 7B parameters

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