Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Decensored language models made using Heretic (https://github.com/p-e-w/heretic)

p-e-w/gpt-oss-20b-heretic

Text Generation • 21B • Updated 4 days ago • 1.15k • 38
p-e-w/Llama-3.1-8B-Instruct-heretic

Text Generation • 8B • Updated 5 days ago • 277 • 3
p-e-w/phi-4-heretic

Text Generation • 15B • Updated 5 days ago • 95 • 3
p-e-w/Qwen3-4B-Instruct-2507-heretic

Text Generation • 4B • Updated 5 days ago • 483 • 12

Running

271

Qwen3 VL Demo

😻

271

Chat with an AI assistant using text and images
Qwen/Qwen3-VL-235B-A22B-Thinking

Image-Text-to-Text • 236B • Updated Oct 4 • 11.2k • • 324
Qwen/Qwen3-VL-235B-A22B-Instruct

Image-Text-to-Text • 236B • Updated Oct 4 • 68.2k • • 313
Qwen/Qwen3-VL-235B-A22B-Thinking-FP8

Image-Text-to-Text • 236B • Updated Oct 9 • 32.4k • 24

Holo2 - Cost-Efficient Models for Cross-Platform Computer-Use Agents

Hcompany/Holo2-4B

Image-Text-to-Text • 4B • Updated 5 days ago • 344 • 13
Hcompany/Holo2-8B

Image-Text-to-Text • 9B • Updated 5 days ago • 128 • 14
Hcompany/Holo2-30B-A3B

Image-Text-to-Text • 31B • Updated 2 days ago • 356 • 28

Models and data associated with DR Tulu, http://allenai-web/papers/drtulu

rl-research/DR-Tulu-8B

8B • Updated 1 day ago • 116 • 22
rl-research/DR-Tulu-SFT-8B

Text Generation • 8B • Updated 1 day ago • 9 • 1
rl-research/dr-tulu-sft-data

Viewer • Updated 1 day ago • 13.1k • 9
rl-research/dr-tulu-rl-data

Viewer • Updated 1 day ago • 4.88k • 1 • 5

Depth Anything 3

Running on Zero

175

Depth Anything 3

🏢

175

Generate depth maps from images using GPU acceleration
depth-anything/DA3NESTED-GIANT-LARGE

Depth Estimation • 2B • Updated 7 days ago • 17k • 19
depth-anything/DA3-GIANT

Depth Estimation • 1B • Updated 6 days ago • 1.45k • 10
depth-anything/DA3-LARGE

Depth Estimation • 0.4B • Updated about 11 hours ago • 2.52k • 8

MiroThinker-v1.0

Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Paper • 2511.11793 • Published 5 days ago • 136
miromind-ai/MiroThinker-v1.0-72B

Text Generation • 73B • Updated about 10 hours ago • 1.38k • 95
miromind-ai/MiroThinker-v1.0-30B

Text Generation • 31B • Updated about 10 hours ago • 963 • 36
miromind-ai/MiroThinker-v1.0-8B

Text Generation • 8B • Updated about 10 hours ago • 743 • 42

Jan-v2-VL: an 8B VLM focused on reliable, many-step task execution.

janhq/Jan-v2-VL-low

Image-Text-to-Text • 9B • Updated 6 days ago • 38 • 12
janhq/Jan-v2-VL-low-gguf

Image-Text-to-Text • 8B • Updated 6 days ago • 4.35k • 6
janhq/Jan-v2-VL-med

Image-Text-to-Text • 9B • Updated 6 days ago • 369 • 11
janhq/Jan-v2-VL-med-gguf

Image-Text-to-Text • 8B • Updated 6 days ago • 8.33k • 11

Qwen/Qwen3-235B-A22B-Thinking-2507-FP8

Text Generation • 235B • Updated Jul 30 • 17.6k • 64
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • 235B • Updated Aug 17 • 58.4k • • 379
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Text Generation • 235B • Updated Sep 17 • 141k • 135
Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated Sep 17 • 118k • • 720

Meta's Llama 3.1 models & evals

meta-llama/Llama-3.1-8B

Text Generation • 8B • Updated Oct 16, 2024 • 590k • • 1.92k
meta-llama/Llama-3.1-70B

Text Generation • 71B • Updated Sep 25, 2024 • 95.6k • 390
meta-llama/Llama-3.1-405B

Text Generation • 406B • Updated Sep 25, 2024 • 62.7k • 948
meta-llama/Llama-3.1-70B-Instruct

Text Generation • 71B • Updated Dec 15, 2024 • 739k • • 861

about 8 hours ago

facebook/sam3

Mask Generation • 0.9B • Updated about 7 hours ago • 8 • 90
Running on L4

15

SAM3 Video Segmentation

🐠

15

Track objects in videos using text prompts
onnx-community/sam3-tracker-ONNX

Mask Generation • Updated about 8 hours ago • 3 • 2
Running

3

SAM3 Tracker WebGPU

🎯

3

Segment and extract parts of images

Decensored language models made using Heretic (https://github.com/p-e-w/heretic)

p-e-w/gpt-oss-20b-heretic

Text Generation • 21B • Updated 4 days ago • 1.15k • 38
p-e-w/Llama-3.1-8B-Instruct-heretic

Text Generation • 8B • Updated 5 days ago • 277 • 3
p-e-w/phi-4-heretic

Text Generation • 15B • Updated 5 days ago • 95 • 3
p-e-w/Qwen3-4B-Instruct-2507-heretic

Text Generation • 4B • Updated 5 days ago • 483 • 12

MiroThinker-v1.0

Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Paper • 2511.11793 • Published 5 days ago • 136
miromind-ai/MiroThinker-v1.0-72B

Text Generation • 73B • Updated about 10 hours ago • 1.38k • 95
miromind-ai/MiroThinker-v1.0-30B

Text Generation • 31B • Updated about 10 hours ago • 963 • 36
miromind-ai/MiroThinker-v1.0-8B

Text Generation • 8B • Updated about 10 hours ago • 743 • 42

Running

271

Qwen3 VL Demo

😻

271

Chat with an AI assistant using text and images
Qwen/Qwen3-VL-235B-A22B-Thinking

Image-Text-to-Text • 236B • Updated Oct 4 • 11.2k • • 324
Qwen/Qwen3-VL-235B-A22B-Instruct

Image-Text-to-Text • 236B • Updated Oct 4 • 68.2k • • 313
Qwen/Qwen3-VL-235B-A22B-Thinking-FP8

Image-Text-to-Text • 236B • Updated Oct 9 • 32.4k • 24

Jan-v2-VL: an 8B VLM focused on reliable, many-step task execution.

janhq/Jan-v2-VL-low

Image-Text-to-Text • 9B • Updated 6 days ago • 38 • 12
janhq/Jan-v2-VL-low-gguf

Image-Text-to-Text • 8B • Updated 6 days ago • 4.35k • 6
janhq/Jan-v2-VL-med

Image-Text-to-Text • 9B • Updated 6 days ago • 369 • 11
janhq/Jan-v2-VL-med-gguf

Image-Text-to-Text • 8B • Updated 6 days ago • 8.33k • 11

Holo2 - Cost-Efficient Models for Cross-Platform Computer-Use Agents

Hcompany/Holo2-4B

Image-Text-to-Text • 4B • Updated 5 days ago • 344 • 13
Hcompany/Holo2-8B

Image-Text-to-Text • 9B • Updated 5 days ago • 128 • 14
Hcompany/Holo2-30B-A3B

Image-Text-to-Text • 31B • Updated 2 days ago • 356 • 28

Qwen/Qwen3-235B-A22B-Thinking-2507-FP8

Text Generation • 235B • Updated Jul 30 • 17.6k • 64
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • 235B • Updated Aug 17 • 58.4k • • 379
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Text Generation • 235B • Updated Sep 17 • 141k • 135
Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated Sep 17 • 118k • • 720

Models and data associated with DR Tulu, http://allenai-web/papers/drtulu

rl-research/DR-Tulu-8B

8B • Updated 1 day ago • 116 • 22
rl-research/DR-Tulu-SFT-8B

Text Generation • 8B • Updated 1 day ago • 9 • 1
rl-research/dr-tulu-sft-data

Viewer • Updated 1 day ago • 13.1k • 9
rl-research/dr-tulu-rl-data

Viewer • Updated 1 day ago • 4.88k • 1 • 5

Meta's Llama 3.1 models & evals

meta-llama/Llama-3.1-8B

Text Generation • 8B • Updated Oct 16, 2024 • 590k • • 1.92k
meta-llama/Llama-3.1-70B

Text Generation • 71B • Updated Sep 25, 2024 • 95.6k • 390
meta-llama/Llama-3.1-405B

Text Generation • 406B • Updated Sep 25, 2024 • 62.7k • 948
meta-llama/Llama-3.1-70B-Instruct

Text Generation • 71B • Updated Dec 15, 2024 • 739k • • 861

Depth Anything 3

Running on Zero

175

Depth Anything 3

🏢

175

Generate depth maps from images using GPU acceleration
depth-anything/DA3NESTED-GIANT-LARGE

Depth Estimation • 2B • Updated 7 days ago • 17k • 19
depth-anything/DA3-GIANT

Depth Estimation • 1B • Updated 6 days ago • 1.45k • 10
depth-anything/DA3-LARGE

Depth Estimation • 0.4B • Updated about 11 hours ago • 2.52k • 8

about 8 hours ago

facebook/sam3

Mask Generation • 0.9B • Updated about 7 hours ago • 8 • 90
Running on L4

15

SAM3 Video Segmentation

🐠

15

Track objects in videos using text prompts
onnx-community/sam3-tracker-ONNX

Mask Generation • Updated about 8 hours ago • 3 • 2
Running

3

SAM3 Tracker WebGPU

🎯

3

Segment and extract parts of images

Previous
1
2
3
...
16,374
Next

Company

TOS Privacy About Jobs

Website

Models Datasets Spaces Pricing Docs