THE MODEL DIRECTORY

Every listing. A closer look.

All 3,558 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 70 of 75 · Coverage limits

Google · Downloadable

tipsv2-l14

VisionImage classificationEmbeddings

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Listed Apr 9, 2026488M parameters

Google · Downloadable

tipsv2-l14-dpt

VisionImage segmentationDepth estimationEmbeddings

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

Listed Apr 9, 2026406M parameters

Google · Downloadable

tipsv2-so400m14

VisionImage classificationEmbeddings

Hugging Face lists its task as zero-shot image classification. See the model card for supported inputs and setup.

Listed Apr 9, 2026862M parameters

Google · Downloadable

tipsv2-so400m14-dpt

VisionImage segmentationDepth estimationEmbeddings

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

Listed Apr 9, 2026533M parameters

NVIDIA · Downloadable

TMR-SOMA-RP-v1

Capabilities unconfirmed

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

Listed Apr 8, 2026Size not disclosed

BAAI · Downloadable

tokenize-anything

Vision

Understands text and images and responds in text.

Listed Dec 14, 2023Size not disclosed

Moondream · Downloadable

tracking

Capabilities unconfirmed

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

Listed Apr 19, 2026194M parameters

M-A-P · Downloadable

transformer_1.3B_baseline

Text generation

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

Listed Sep 10, 20251.3B parameters

M-A-P · Downloadable

transformer_340M_baseline

Text generation

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

Listed Sep 11, 2025340M parameters

Google · Downloadable

translategemma-12b-it

Vision

Understands text and images and responds in text.

Listed Jan 12, 202612B parameters

Google · Downloadable

translategemma-27b-it

Vision

Understands text and images and responds in text.

Listed Jan 12, 202627B parameters

Google · Downloadable

translategemma-4b-it

Vision

Understands text and images and responds in text.

Listed Jan 12, 20264B parameters

NVIDIA · Downloadable

transolver_drivaerml

Capabilities unconfirmed

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

Listed Apr 29, 2026Size not disclosed

M-A-P · Downloadable

TreePO-Qwen2.5-7B

Text generation

Generates text for conversations and writing.

Listed Aug 26, 20257B parameters

M-A-P · Downloadable

TreePO-Qwen2.5-7B_fixed-div

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 Aug 26, 20257B parameters

M-A-P · Downloadable

TreePO-Qwen2.5-7B_GRPO-TreePO-Sampling

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 Sep 4, 20257B parameters

M-A-P · Downloadable

TreePO-Qwen2.5-7B_Low_Prob_Encourage

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 Sep 4, 20257B parameters

M-A-P · Downloadable

TreePO-Qwen2.5-7B_Naive2Low_Scheduler

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 Sep 4, 20257B parameters

Microsoft · Downloadable

TRELLIS-image-large

3D generation

Creates 3D assets. Check the model card for supported inputs and output formats.

Listed Dec 2, 2024Size not disclosed

Microsoft · Downloadable

TRELLIS-text-base

3D generation

Creates 3D assets. Check the model card for supported inputs and output formats.

Listed Mar 24, 2025Size not disclosed

Microsoft · Downloadable

TRELLIS-text-large

3D generation

Creates 3D assets. Check the model card for supported inputs and output formats.

Listed Mar 24, 2025Size not disclosed

Microsoft · Downloadable

TRELLIS-text-xlarge

3D generation

Creates 3D assets. Check the model card for supported inputs and output formats.

Listed Mar 24, 2025Size not disclosed

Microsoft · Downloadable

TRELLIS.2-4B

3D generation

Turns an image into a textured 3D asset. Designed for creating meshes and materials.

Listed Dec 1, 20254B parameters

Meta · Downloadable

tribev2

Capabilities unconfirmed

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

Listed Mar 24, 2026Size not disclosed

Meta · Downloadable

tribev2-mini

Capabilities unconfirmed

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

Listed Mar 30, 2026Size not disclosed

Meta · Downloadable

tribev2-subcortical

Capabilities unconfirmed

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

Listed May 13, 2026Size not disclosed

OpenBMB · Downloadable

Trident-Qwen3VL-2B

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Oct 12, 20262B parameters

Stability AI · Downloadable

TripoSR

3D generation

Creates 3D assets. Check the model card for supported inputs and output formats.

Listed Feb 29, 2024Size not disclosed

BRIA AI · Downloadable

trustmark-weights

Capabilities unconfirmed

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

Listed Aug 6, 2026Size not disclosed

k2-fsa · Downloadable

TTS_eval_models

Audio generation

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

Listed Apr 3, 2025Size not disclosed

Kyutai · Downloadable

tts-0.75b-en-public

Audio generation

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

Listed Jul 15, 2025750M parameters

Kyutai · Downloadable

tts-1.6b-en_fr

Audio generation

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

Listed Jun 30, 20251.6B parameters

Kyutai · Downloadable

tts-voices

Capabilities unconfirmed

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

Listed Jul 1, 2025Size not disclosed

inclusionAI · Downloadable

TwinFlow

Image generation

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

Listed Oct 24, 2025Size not disclosed

inclusionAI · Downloadable

TwinFlow-Z-Image-Turbo

Image generation

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

Listed Dec 23, 2025Size not disclosed

Google · Downloadable

txgemma-27b-chat

Text generation

Generates text for conversations and writing.

Listed Mar 21, 202527B parameters

Google · Downloadable

txgemma-27b-predict

Text generation

Generates text for conversations and writing.

Listed Mar 21, 202527B parameters

Google · Downloadable

txgemma-2b-predict

Text generation

Generates text for conversations and writing.

Listed Mar 21, 20252B parameters

Google · Downloadable

txgemma-9b-chat

Text generation

Generates text for conversations and writing.

Listed Mar 21, 20259B parameters

Google · Downloadable

txgemma-9b-predict

Text generation

Generates text for conversations and writing.

Listed Mar 21, 20259B parameters

Tencent · Downloadable

UI-Mate-27B

Vision

Understands text and images and responds in text.

Listed Aug 14, 202627B parameters

Tencent · Downloadable

UI-Mate-9B

Vision

Understands text and images and responds in text.

Listed Aug 14, 20269B parameters

Tencent · Downloadable

UI-Mate-democua-27B

Vision

Understands text and images and responds in text.

Listed Aug 14, 202627B parameters

inclusionAI · Downloadable

UI-Venus-1.5-2B

Vision

Understands text and images and responds in text.

Listed Feb 9, 20262B parameters

inclusionAI · Downloadable

UI-Venus-1.5-30B-A3B

Vision

Understands text and images and responds in text.

Listed Feb 9, 202630B parameters

inclusionAI · Downloadable

UI-Venus-1.5-8B

Vision

Understands text and images and responds in text.

Listed Feb 9, 20268B parameters

inclusionAI · Downloadable

UI-Venus-2-9B

Vision

Understands text and images and responds in text.

Listed Aug 26, 20269B parameters

inclusionAI · Downloadable

UI-Venus-Ground-72B

Vision

Understands text and images and responds in text.

Listed Aug 16, 202572B parameters

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