Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

ConnorYU/qwen3.5-9b-insecure-v3-sec-ih_424

Image-Text-to-Text • 9B • Updated Aug 18 • 10
ConnorYU/qwen3.5-9b-insecure-v3-sec-ih

Image-Text-to-Text • 9B • Updated Aug 17 • 9
ConnorYU/qwen3.5-9b-insecure-v3-sec

Image-Text-to-Text • 10B • Updated Jun 13 • 12
ConnorYU/qwen3.5-4b-insecure-v3-sec-ih

Image-Text-to-Text • 5B • Updated Aug 10 • 7

ImageReferenceEdit

Running on Zero

Agents

21

RefControl FLUX.2 Klein - Reference + Depth

🎭

21

Re-pose a subject via a depth map, keep its identity
Running on Zero

MCP

266

MiniMax-H3 Ultra Fast

⚡

266

Ultra-fast local NVFP4 video + synchronized audio generation

pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 7.05M • 4.79k
pyannote/segmentation-3.0

Voice Activity Detection • Updated May 10, 2024 • 5.26M • 2.46k

Dataset for Multimodal project

JetSpec releases

Public JetSpec checkpoints: causal parallel drafters for lossless speculative decoding. Good at tree drafting for ultra-low latency.

about 7 hours ago

JetSpec/jetspec-Qwen3.6-35B-A3B

0.5B • Updated Jun 17 • 90 • 11
JetSpec/jetspec-qwen3-30b-a3b

0.5B • Updated Jun 11 • 25
JetSpec/jetspec-qwen3-8b

1B • Updated May 18 • 549 • 2
JetSpec/jetspec-Step-3.7-Flash

0.9B • Updated Jun 15 • 19 • 3

mradermacher/community-blend-qwen3-8b-GGUF

8B • Updated Mar 1 • 310 • 1
mradermacher/qwen8b_secreason-GGUF

8B • Updated Jul 11, 2025 • 161 • 2

Qwen3.8-27B on RTX 5090

SGLang b12x + all-NVFP4. +25 to +33% decode vs stock on fixed prompts. github.com/thomgardiner/sglang-sm120-nvfp4

thomasgardiner/Qwen3.8-27B-NVFP4-all

Text Generation • 15B • Updated Sep 7 • 249 • 1
thomasgardiner/Qwen3.8-27B-DFlash2-FP8

Text Generation • 2B • Updated Sep 7 • 746 • 2
RadixArk/Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Aug 22 • 982k • 121
incoai/Qwen3.8-27B-DFlash2

Text Generation • 2B • Updated Sep 17 • 374k • 294

lambda-llm-datasets

These datasets are used to train lambda-llm.

KeisukeMiyamoto/lambda-corpus

Viewer • Updated Aug 22 • 18.9M • 170
KeisukeMiyamoto/lambda-chat

Viewer • Updated Aug 22 • 187k • 72
KeisukeMiyamoto/SyntheticTextbook-jp

Viewer • Updated Aug 22 • 1.09M • 122
KeisukeMiyamoto/CleanedWiki-jp

Viewer • Updated Aug 22 • 1.8M • 161

ConnorYU/qwen3.5-9b-insecure-v3-sec-ih_424

Image-Text-to-Text • 9B • Updated Aug 18 • 10
ConnorYU/qwen3.5-9b-insecure-v3-sec-ih

Image-Text-to-Text • 9B • Updated Aug 17 • 9
ConnorYU/qwen3.5-9b-insecure-v3-sec

Image-Text-to-Text • 10B • Updated Jun 13 • 12
ConnorYU/qwen3.5-4b-insecure-v3-sec-ih

Image-Text-to-Text • 5B • Updated Aug 10 • 7

JetSpec releases

Public JetSpec checkpoints: causal parallel drafters for lossless speculative decoding. Good at tree drafting for ultra-low latency.

about 7 hours ago

JetSpec/jetspec-Qwen3.6-35B-A3B

0.5B • Updated Jun 17 • 90 • 11
JetSpec/jetspec-qwen3-30b-a3b

0.5B • Updated Jun 11 • 25
JetSpec/jetspec-qwen3-8b

1B • Updated May 18 • 549 • 2
JetSpec/jetspec-Step-3.7-Flash

0.9B • Updated Jun 15 • 19 • 3

ImageReferenceEdit

Running on Zero

Agents

21

RefControl FLUX.2 Klein - Reference + Depth

🎭

21

Re-pose a subject via a depth map, keep its identity
Running on Zero

MCP

266

MiniMax-H3 Ultra Fast

⚡

266

Ultra-fast local NVFP4 video + synchronized audio generation

mradermacher/community-blend-qwen3-8b-GGUF

8B • Updated Mar 1 • 310 • 1
mradermacher/qwen8b_secreason-GGUF

8B • Updated Jul 11, 2025 • 161 • 2

pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 7.05M • 4.79k
pyannote/segmentation-3.0

Voice Activity Detection • Updated May 10, 2024 • 5.26M • 2.46k

Qwen3.8-27B on RTX 5090

SGLang b12x + all-NVFP4. +25 to +33% decode vs stock on fixed prompts. github.com/thomgardiner/sglang-sm120-nvfp4

thomasgardiner/Qwen3.8-27B-NVFP4-all

Text Generation • 15B • Updated Sep 7 • 249 • 1
thomasgardiner/Qwen3.8-27B-DFlash2-FP8

Text Generation • 2B • Updated Sep 7 • 746 • 2
RadixArk/Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Aug 22 • 982k • 121
incoai/Qwen3.8-27B-DFlash2

Text Generation • 2B • Updated Sep 17 • 374k • 294

Dataset for Multimodal project

lambda-llm-datasets

These datasets are used to train lambda-llm.

KeisukeMiyamoto/lambda-corpus

Viewer • Updated Aug 22 • 18.9M • 170
KeisukeMiyamoto/lambda-chat

Viewer • Updated Aug 22 • 187k • 72
KeisukeMiyamoto/SyntheticTextbook-jp

Viewer • Updated Aug 22 • 1.09M • 122
KeisukeMiyamoto/CleanedWiki-jp

Viewer • Updated Aug 22 • 1.8M • 161

Previous
1
...
1,559
1,560
1,561
1,562
1,563
...
24,468
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs