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

Collections

Discover the best community collections!

Collections trending this week

Micro-Action Understanding

kunli-cs/MA-52

Updated Aug 30, 2025 • 64 • 7
kunli-cs/MMA-52

Preview • Updated Jul 25, 2025 • 19 • 3
kunli-cs/MA-Bench

Viewer • Updated May 12 • 1k • 742 • 1

Run SDXL / Pony / Illustrate models on qualcomm devices (8gen3 and above)

Mr-J-369/PonyRealismV2.3-PONY-qnn2.28

Text-to-Image • Updated Jun 19 • 1
Mr-J-369/intorealismUltra_v11-SDXL-qnn2.28

Text-to-Image • Updated 21 days ago • 5
Mr-J-369/jrdRenderspecXLTURBO-SDXL-qnn2.28

Text-to-Image • Updated Jun 19 • 1
Mr-J-369/lustifySDXLNSFW_apexV8-SDXL-qnn2.28

Text-to-Image • Updated Jun 19 • 4

Optimized for cuda acceleration

srswti/blackbird-she-doesnt-refuse-21b-cu

Text Generation • 21B • Updated Apr 30 • 16 • 1
srswti/blackbird-she-doesnt-refuse-36b-a3b-cu

Text Generation • 36B • Updated Apr 30 • 12
srswti/axe-veloce-37b

Image-Text-to-Text • 35B • Updated Apr 30 • 5
srswti/axe-superveloce-37b

Image-Text-to-Text • 35B • Updated Apr 30 • 50

Nemotron Reward Modeling

Human preference data, reward model training sets, and generative reward modeling data for training Nemotron reward models.

nvidia/HelpSteer

Viewer • Updated Dec 18, 2024 • 37.1k • 1.6k • 251
nvidia/HelpSteer2

Viewer • Updated Dec 18, 2024 • 21.4k • 9.54k • 454
nvidia/HelpSteer3

Viewer • Updated Nov 16, 2025 • 133k • 5.76k • 115
nvidia/Nemotron-RLHF-GenRM-v1

Viewer • Updated Mar 11 • 199k • 432 • 5

Gorgeous Models

DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

Image-Text-to-Text • 27B • Updated 4 days ago • 1.55M • 1.42k
black-forest-labs/FLUX.2-klein-9B

Image-to-Image • 9B • Updated Feb 24 • 335k • • 1.16k
FlareRebellion/WeirdCompound-v1.7-24b

Text Generation • 24B • Updated Oct 13, 2025 • 213 • • 53
Naphula/Goetia-24B-v1.2

Text Generation • 24B • Updated May 1 • 16 • 18

Model merges and stuff

ShyliaSafetensors/Ariel-Alloy-V1-24B-Heretic

Text Generation • 24B • Updated Jun 16 • 106 • 5
ShyliaSafetensors/TritonModelStock-V2.1-24B

Text Generation • 24B • Updated Jun 16 • 105 • 3
ShyliaSafetensors/TritonModelStock-V1-24B

Text Generation • 24B • Updated Jun 12 • 9 • 1
ShyliaSafetensors/VeryWeirdDolphinMix-V1-24B-Heretic

Text Generation • 24B • Updated May 11 • 69 • • 9

MiroThinker-1.7

miromind-ai/MiroThinker-1.7

Text Generation • 235B • Updated Apr 13 • 186 • 145
miromind-ai/MiroThinker-1.7-mini

Text Generation • 31B • Updated Apr 13 • 538 • 104

Nemotron Vision-Language

Image-text paired datasets for building vision-language models (VLMs).

nvidia/Llama-Nemotron-VLM-Dataset-v1

Viewer • Updated Oct 22, 2025 • 2.86M • 2.28k • 167
nvidia/Nemotron-VLM-Dataset-v2

Viewer • Updated Dec 18, 2025 • 4.58M • 3.57k • 94
nvidia/Nemotron-Image-Training-v3

Viewer • Updated Apr 28 • 6.92M • 2.23k • 78

This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e

Jackrong/Qwopus3.6-27B-v2

Image-Text-to-Text • 28B • Updated Jun 23 • 5.37k • 60
Jackrong/Qwopus3.6-27B-v2-GGUF

Image-Text-to-Text • 27B • Updated 26 days ago • 10.8k • 251
Jackrong/Qwopus3.6-27B-v2-FP8

Image-Text-to-Text • 28B • Updated Jun 23 • 2.43k • 28
Jackrong/Qwopus3.6-35B-A3B-v1

Image-Text-to-Text • 36B • Updated May 15 • 3.55k • 61

swe-zero-to-swe-hero

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496)

nvidia/SWE-Zero-openhands-trajectories

Viewer • Updated May 5 • 318k • 2.46k • 17
nvidia/SWE-Hero-openhands-trajectories

Viewer • Updated May 8 • 34.3k • 1.74k • 21
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

Paper • 2604.01496 • Published Apr 2 • 2

Micro-Action Understanding

kunli-cs/MA-52

Updated Aug 30, 2025 • 64 • 7
kunli-cs/MMA-52

Preview • Updated Jul 25, 2025 • 19 • 3
kunli-cs/MA-Bench

Viewer • Updated May 12 • 1k • 742 • 1

Model merges and stuff

ShyliaSafetensors/Ariel-Alloy-V1-24B-Heretic

Text Generation • 24B • Updated Jun 16 • 106 • 5
ShyliaSafetensors/TritonModelStock-V2.1-24B

Text Generation • 24B • Updated Jun 16 • 105 • 3
ShyliaSafetensors/TritonModelStock-V1-24B

Text Generation • 24B • Updated Jun 12 • 9 • 1
ShyliaSafetensors/VeryWeirdDolphinMix-V1-24B-Heretic

Text Generation • 24B • Updated May 11 • 69 • • 9

Run SDXL / Pony / Illustrate models on qualcomm devices (8gen3 and above)

Mr-J-369/PonyRealismV2.3-PONY-qnn2.28

Text-to-Image • Updated Jun 19 • 1
Mr-J-369/intorealismUltra_v11-SDXL-qnn2.28

Text-to-Image • Updated 21 days ago • 5
Mr-J-369/jrdRenderspecXLTURBO-SDXL-qnn2.28

Text-to-Image • Updated Jun 19 • 1
Mr-J-369/lustifySDXLNSFW_apexV8-SDXL-qnn2.28

Text-to-Image • Updated Jun 19 • 4

MiroThinker-1.7

miromind-ai/MiroThinker-1.7

Text Generation • 235B • Updated Apr 13 • 186 • 145
miromind-ai/MiroThinker-1.7-mini

Text Generation • 31B • Updated Apr 13 • 538 • 104

Optimized for cuda acceleration

srswti/blackbird-she-doesnt-refuse-21b-cu

Text Generation • 21B • Updated Apr 30 • 16 • 1
srswti/blackbird-she-doesnt-refuse-36b-a3b-cu

Text Generation • 36B • Updated Apr 30 • 12
srswti/axe-veloce-37b

Image-Text-to-Text • 35B • Updated Apr 30 • 5
srswti/axe-superveloce-37b

Image-Text-to-Text • 35B • Updated Apr 30 • 50

Nemotron Vision-Language

Image-text paired datasets for building vision-language models (VLMs).

nvidia/Llama-Nemotron-VLM-Dataset-v1

Viewer • Updated Oct 22, 2025 • 2.86M • 2.28k • 167
nvidia/Nemotron-VLM-Dataset-v2

Viewer • Updated Dec 18, 2025 • 4.58M • 3.57k • 94
nvidia/Nemotron-Image-Training-v3

Viewer • Updated Apr 28 • 6.92M • 2.23k • 78

Nemotron Reward Modeling

Human preference data, reward model training sets, and generative reward modeling data for training Nemotron reward models.

nvidia/HelpSteer

Viewer • Updated Dec 18, 2024 • 37.1k • 1.6k • 251
nvidia/HelpSteer2

Viewer • Updated Dec 18, 2024 • 21.4k • 9.54k • 454
nvidia/HelpSteer3

Viewer • Updated Nov 16, 2025 • 133k • 5.76k • 115
nvidia/Nemotron-RLHF-GenRM-v1

Viewer • Updated Mar 11 • 199k • 432 • 5

This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e

Jackrong/Qwopus3.6-27B-v2

Image-Text-to-Text • 28B • Updated Jun 23 • 5.37k • 60
Jackrong/Qwopus3.6-27B-v2-GGUF

Image-Text-to-Text • 27B • Updated 26 days ago • 10.8k • 251
Jackrong/Qwopus3.6-27B-v2-FP8

Image-Text-to-Text • 28B • Updated Jun 23 • 2.43k • 28
Jackrong/Qwopus3.6-35B-A3B-v1

Image-Text-to-Text • 36B • Updated May 15 • 3.55k • 61

Gorgeous Models

DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

Image-Text-to-Text • 27B • Updated 4 days ago • 1.55M • 1.42k
black-forest-labs/FLUX.2-klein-9B

Image-to-Image • 9B • Updated Feb 24 • 335k • • 1.16k
FlareRebellion/WeirdCompound-v1.7-24b

Text Generation • 24B • Updated Oct 13, 2025 • 213 • • 53
Naphula/Goetia-24B-v1.2

Text Generation • 24B • Updated May 1 • 16 • 18

swe-zero-to-swe-hero

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496)

nvidia/SWE-Zero-openhands-trajectories

Viewer • Updated May 5 • 318k • 2.46k • 17
nvidia/SWE-Hero-openhands-trajectories

Viewer • Updated May 8 • 34.3k • 1.74k • 21
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

Paper • 2604.01496 • Published Apr 2 • 2

Previous
1
...
29
30
31
32
33
...
22,241
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs