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

Gemma4-Aquarion

Contains FP8/FP4, INT8/INT4 weight-only safetensors as well as GGUF/APEX quants of the Gemma4 series.

Rin247/gemma-4-31B-it-Uncensored-Aquarion-FP8

Image-Text-to-Text • 31B • Updated Aug 31 • 18
Rin247/gemma-4-31B-it-Uncensored-Aquarion-FP4

Image-Text-to-Text • 16B • Updated Aug 31 • 11
Rin247/gemma-4-31B-it-Uncensored-Aquarion-INT8

Image-Text-to-Text • 31B • Updated Aug 31 • 9
Rin247/gemma-4-31B-it-Uncensored-Aquarion-INT4

Image-Text-to-Text • 16B • Updated Aug 31 • 8

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

Sentence Similarity • 0.1B • Updated Jan 28 • 45M • • 1.48k

tencent/WeMM-Embedding-9B

Feature Extraction • 9B • Updated Sep 3 • 4.54k • 140
Qwen/Qwen3-Reranker-8B

Text Ranking • 8B • Updated Apr 16 • 263k • 289
Qwen/Qwen3-Embedding-8B

Feature Extraction • 8B • Updated Jul 7, 2025 • 2.03M • • 834
intfloat/multilingual-e5-large

Feature Extraction • 0.6B • Updated Apr 2 • 6.68M • • 1.28k

Running

Featured

636

Microduck Sandbox

🐤

636

Showcase a bold landing page with stylized title and button

p4ik/Qwen3.8-27B-MLX-OptiQ-5bit

Image-Text-to-Text • 27B • Updated Aug 29 • 137
p4ik/Qwen3.8-27B-MLX-OptiQ-4bit

Image-Text-to-Text • 27B • Updated Aug 29 • 240
p4ik/Qwen3.8-27B-MLX-8bit

Image-Text-to-Text • 27B • Updated Aug 29 • 87
p4ik/Qwen3.8-27B-MLX-4bit

Image-Text-to-Text • 27B • Updated Aug 29 • 100

Frozen features read chest radiographs

A 339 KB linear probe on a frozen general-purpose backbone: 0.7590 on the official ChestX-ray14 split, against 0.7451 fine-tuned.

Paused

Agents

1

ChestX-ray14 frozen probe

🫁

1

339 KB linear probe beats a fine-tuned ResNet-50
RiverRider/srt-cxr14-linear-probe

Image Classification • Updated Sep 5 • 2
RiverRider/srt-cxr14-frozen-probe

Updated Aug 30 • 158 • 2
RiverRider/srt-cxr14-pooled-probe

Image Classification • Updated Sep 5

EllaPriest45/Krea2_Characters

Updated 10 days ago • 91
spyrostheboss/Charithra_Chandran_Krea_2_LoRA

Text-to-Image • Updated Aug 30
spyrostheboss/Maitreyi_Ramakrishnan_Krea_2_LoRA

Text-to-Image • Updated Aug 30 • 2
AdwolfCzar/k2-proximacena-grounded-v2-full

Updated Aug 5

Spectral Surgery — Commonsense Reasoning

Qwen3-8B adapters trained on Commonsense170K, with post-hoc Spectral Surgery evaluation across eight commonsense reasoning benchmarks.

tianzl66/Qwen3-8B-CommonSense170K-LoRA

Updated Aug 29
tianzl66/Qwen3-8B-CommonSense170K-Spectral-Surgery

Updated Aug 29
tianzl66/Llama-3.1-8B-Instruct-CommonSense170K-LoRA-Epoch1

Updated Sep 5 • 13
tianzl66/Llama-3.1-8B-Instruct-CommonSense170K-LoRA-Epoch2

Updated Sep 5 • 9

Contains FP8/FP4, INT8/INT4 weight-only safetensors quants of the Qwen3 series, used by Anima, Krea2, Z-Image, Klein and many others.

Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-FP8

8B • Updated Aug 30 • 23
Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-FP4

4B • Updated Aug 30 • 138 • 1
Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-INT8

8B • Updated Aug 30 • 81 • 3
Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-INT4

4B • Updated Aug 30 • 10

Conditional Flow Matching for Engineering Inverse Design

Models, datasets, and reproducibility artifacts for the EngOpt 2026 conditional flow-matching paper.

IDEALLab/engiopt-engopt2026-flow-matching-2d-cond

Updated Aug 30
IDEALLab/engiopt-engopt2026-diffusion-2d-cond

Updated Aug 28
IDEALLab/engiopt-engopt2026-cgan-cnn-2d

Updated Aug 28
IDEALLab/beams_2d_50_100_v0

Viewer • Updated Apr 23, 2025 • 4.85k • 1.66k

Gemma4-Aquarion

Contains FP8/FP4, INT8/INT4 weight-only safetensors as well as GGUF/APEX quants of the Gemma4 series.

Rin247/gemma-4-31B-it-Uncensored-Aquarion-FP8

Image-Text-to-Text • 31B • Updated Aug 31 • 18
Rin247/gemma-4-31B-it-Uncensored-Aquarion-FP4

Image-Text-to-Text • 16B • Updated Aug 31 • 11
Rin247/gemma-4-31B-it-Uncensored-Aquarion-INT8

Image-Text-to-Text • 31B • Updated Aug 31 • 9
Rin247/gemma-4-31B-it-Uncensored-Aquarion-INT4

Image-Text-to-Text • 16B • Updated Aug 31 • 8

Frozen features read chest radiographs

A 339 KB linear probe on a frozen general-purpose backbone: 0.7590 on the official ChestX-ray14 split, against 0.7451 fine-tuned.

Paused

Agents

1

ChestX-ray14 frozen probe

🫁

1

339 KB linear probe beats a fine-tuned ResNet-50
RiverRider/srt-cxr14-linear-probe

Image Classification • Updated Sep 5 • 2
RiverRider/srt-cxr14-frozen-probe

Updated Aug 30 • 158 • 2
RiverRider/srt-cxr14-pooled-probe

Image Classification • Updated Sep 5

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

Sentence Similarity • 0.1B • Updated Jan 28 • 45M • • 1.48k

EllaPriest45/Krea2_Characters

Updated 10 days ago • 91
spyrostheboss/Charithra_Chandran_Krea_2_LoRA

Text-to-Image • Updated Aug 30
spyrostheboss/Maitreyi_Ramakrishnan_Krea_2_LoRA

Text-to-Image • Updated Aug 30 • 2
AdwolfCzar/k2-proximacena-grounded-v2-full

Updated Aug 5

tencent/WeMM-Embedding-9B

Feature Extraction • 9B • Updated Sep 3 • 4.54k • 140
Qwen/Qwen3-Reranker-8B

Text Ranking • 8B • Updated Apr 16 • 263k • 289
Qwen/Qwen3-Embedding-8B

Feature Extraction • 8B • Updated Jul 7, 2025 • 2.03M • • 834
intfloat/multilingual-e5-large

Feature Extraction • 0.6B • Updated Apr 2 • 6.68M • • 1.28k

Spectral Surgery — Commonsense Reasoning

Qwen3-8B adapters trained on Commonsense170K, with post-hoc Spectral Surgery evaluation across eight commonsense reasoning benchmarks.

tianzl66/Qwen3-8B-CommonSense170K-LoRA

Updated Aug 29
tianzl66/Qwen3-8B-CommonSense170K-Spectral-Surgery

Updated Aug 29
tianzl66/Llama-3.1-8B-Instruct-CommonSense170K-LoRA-Epoch1

Updated Sep 5 • 13
tianzl66/Llama-3.1-8B-Instruct-CommonSense170K-LoRA-Epoch2

Updated Sep 5 • 9

Running

Featured

636

Microduck Sandbox

🐤

636

Showcase a bold landing page with stylized title and button

Contains FP8/FP4, INT8/INT4 weight-only safetensors quants of the Qwen3 series, used by Anima, Krea2, Z-Image, Klein and many others.

Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-FP8

8B • Updated Aug 30 • 23
Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-FP4

4B • Updated Aug 30 • 138 • 1
Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-INT8

8B • Updated Aug 30 • 81 • 3
Rin247/Qwen3-VL-8B-Instruct-Uncensored-Aquarion-INT4

4B • Updated Aug 30 • 10

p4ik/Qwen3.8-27B-MLX-OptiQ-5bit

Image-Text-to-Text • 27B • Updated Aug 29 • 137
p4ik/Qwen3.8-27B-MLX-OptiQ-4bit

Image-Text-to-Text • 27B • Updated Aug 29 • 240
p4ik/Qwen3.8-27B-MLX-8bit

Image-Text-to-Text • 27B • Updated Aug 29 • 87
p4ik/Qwen3.8-27B-MLX-4bit

Image-Text-to-Text • 27B • Updated Aug 29 • 100

Conditional Flow Matching for Engineering Inverse Design

Models, datasets, and reproducibility artifacts for the EngOpt 2026 conditional flow-matching paper.

IDEALLab/engiopt-engopt2026-flow-matching-2d-cond

Updated Aug 30
IDEALLab/engiopt-engopt2026-diffusion-2d-cond

Updated Aug 28
IDEALLab/engiopt-engopt2026-cgan-cnn-2d

Updated Aug 28
IDEALLab/beams_2d_50_100_v0

Viewer • Updated Apr 23, 2025 • 4.85k • 1.66k

Previous
1
...
1,343
1,344
1,345
1,346
1,347
...
24,088
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs