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

Collections

Discover the best community collections!

Collections trending this week

Do Conversational Agents Need Explicit Memory? A Controlled Comparison with Raw-History Retrieval

Paper • 2610.24671 • Published 21 days ago • 1

How to Reach Non-Followers on Instagram Reels

https://www.digivanta.co/blog/instagram-reels-not-reaching-non-followers

Swift fine-tunes of Qwen3.8-27B (PARO-quantised radiance containers).

hugypufy/Swift-Qwen3.8-27B-PARO-int5

Image-Text-to-Text • 7B • Updated Sep 17 • 182 • 3
hugypufy/Swift-Qwen3.8-27B-PARO-MXFP6

Image-Text-to-Text • 21B • Updated Sep 17 • 153 • 5

tencent/Hy-Memory-30B-A3B

Text Generation • 30B • Updated 22 days ago • 6.75k • 324
MemTensor/MemT-1.0-Nano

Text Generation • 35B • Updated 18 days ago • 87.3k • 172

Cartographics Base Model Atlases

Atlases created for the base models you love and fine-tune. Atlas your own fine-tune for comparison with ~3 minutes of ZeroGPU time. The CPU is on us!

about 16 hours ago

Running on Zero

Agents

4

Cartographics

🌍

4

Build custom neural atlases for language model activations
juiceb0xc0de/qwen3.8-27b-cgs-atlas

Viewer • Updated 12 days ago • 4.82M • 103
juiceb0xc0de/qwen3.5-27b-cgs-atlas

Viewer • Updated 15 days ago • 4.82M • 177
juiceb0xc0de/qwen3.5-9b-cgs-atlas

Viewer • Updated 14 days ago • 1.74M • 100

nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-FP8

Image-Text-to-Text • 13B • Updated Sep 2 • 3.17k • 57
nvidia/Nemotron-3.5-Parse

Image-Text-to-Text • 0.6B • Updated 2 days ago • 17.7k • 149

WhiteDevil010/icrm-hitek-full-db-mixed-bucket

227 GB

MXFP6 PARO-quantised radiance containers for Qwen3.8-27B.

hugypufy/Qwen3.8-27B-PARO-MXFP6

Image-Text-to-Text • 21B • Updated Sep 17 • 84 • 2
hugypufy/Swift-Qwen3.8-27B-PARO-MXFP6

Image-Text-to-Text • 21B • Updated Sep 17 • 153 • 5

MXFP4 + learned metadata + learned Givens rotations. radiance containers, AMD RDNA4 (gfx1201), single-GPU.

hugypufy/Qwen3.8-27B-DFLASH2-PARO-M2XFP4

Text Generation • Updated 14 days ago
hugypufy/Qwen3.8-27B-PARO-M2XFP4

Text Generation • Updated 14 days ago
hugypufy/Qwen3.8-27B-DFLASH2-M2XFP4

Text Generation • Updated 14 days ago
hugypufy/Qwen3.8-27B-M2XFP4

Text Generation • Updated 14 days ago

Tiny local decision models by Labqoat: calibrated answers in one forward pass, on NVIDIA, Mac and llama.cpp.

labqoat/squad-0.8b

Image-Text-to-Text • 0.9B • Updated 11 days ago • 247
labqoat/squad-0.8b-MLX

0.8B • Updated 11 days ago • 69
labqoat/squad-0.8b-GGUF

10.6M • Updated 11 days ago • 1.36k
labqoat/qev-0.8b

Image-Text-to-Text • 0.9B • Updated 15 days ago • 668 • 17

Do Conversational Agents Need Explicit Memory? A Controlled Comparison with Raw-History Retrieval

Paper • 2610.24671 • Published 21 days ago • 1

nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-FP8

Image-Text-to-Text • 13B • Updated Sep 2 • 3.17k • 57
nvidia/Nemotron-3.5-Parse

Image-Text-to-Text • 0.6B • Updated 2 days ago • 17.7k • 149

How to Reach Non-Followers on Instagram Reels

https://www.digivanta.co/blog/instagram-reels-not-reaching-non-followers

WhiteDevil010/icrm-hitek-full-db-mixed-bucket

227 GB

Swift fine-tunes of Qwen3.8-27B (PARO-quantised radiance containers).

hugypufy/Swift-Qwen3.8-27B-PARO-int5

Image-Text-to-Text • 7B • Updated Sep 17 • 182 • 3
hugypufy/Swift-Qwen3.8-27B-PARO-MXFP6

Image-Text-to-Text • 21B • Updated Sep 17 • 153 • 5

MXFP6 PARO-quantised radiance containers for Qwen3.8-27B.

hugypufy/Qwen3.8-27B-PARO-MXFP6

Image-Text-to-Text • 21B • Updated Sep 17 • 84 • 2
hugypufy/Swift-Qwen3.8-27B-PARO-MXFP6

Image-Text-to-Text • 21B • Updated Sep 17 • 153 • 5

tencent/Hy-Memory-30B-A3B

Text Generation • 30B • Updated 22 days ago • 6.75k • 324
MemTensor/MemT-1.0-Nano

Text Generation • 35B • Updated 18 days ago • 87.3k • 172

MXFP4 + learned metadata + learned Givens rotations. radiance containers, AMD RDNA4 (gfx1201), single-GPU.

hugypufy/Qwen3.8-27B-DFLASH2-PARO-M2XFP4

Text Generation • Updated 14 days ago
hugypufy/Qwen3.8-27B-PARO-M2XFP4

Text Generation • Updated 14 days ago
hugypufy/Qwen3.8-27B-DFLASH2-M2XFP4

Text Generation • Updated 14 days ago
hugypufy/Qwen3.8-27B-M2XFP4

Text Generation • Updated 14 days ago

Cartographics Base Model Atlases

Atlases created for the base models you love and fine-tune. Atlas your own fine-tune for comparison with ~3 minutes of ZeroGPU time. The CPU is on us!

about 16 hours ago

Running on Zero

Agents

4

Cartographics

🌍

4

Build custom neural atlases for language model activations
juiceb0xc0de/qwen3.8-27b-cgs-atlas

Viewer • Updated 12 days ago • 4.82M • 103
juiceb0xc0de/qwen3.5-27b-cgs-atlas

Viewer • Updated 15 days ago • 4.82M • 177
juiceb0xc0de/qwen3.5-9b-cgs-atlas

Viewer • Updated 14 days ago • 1.74M • 100

Tiny local decision models by Labqoat: calibrated answers in one forward pass, on NVIDIA, Mac and llama.cpp.

labqoat/squad-0.8b

Image-Text-to-Text • 0.9B • Updated 11 days ago • 247
labqoat/squad-0.8b-MLX

0.8B • Updated 11 days ago • 69
labqoat/squad-0.8b-GGUF

10.6M • Updated 11 days ago • 1.36k
labqoat/qev-0.8b

Image-Text-to-Text • 0.9B • Updated 15 days ago • 668 • 17

Previous
1
...
472
473
474
475
476
...
24,628
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs