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

wnxsa/ada_atilgan

Updated May 30
wnxsa/ezgi_akliman

Updated May 29
wnxsa/buse_ortakci

Updated Jun 6
wnxsa/buse_balkan

Updated Jun 25

Collection of artifacts for "SynthTools: A Framework for Scaling Synthetic Tools for Agent Development"

Awesome Apple M1 Pro 32Gb local LLMs collection

Hardware: Apple Macbook Pro 14', M1 Pro chip 32Gb 14GPU. Clients: VS Code + Continue + Zoo Code (ex. Roo Code). Local LLM provider: oMLX.

alexgusevski/Qwen2.5-Coder-3B-Instruct-q6-mlx

Text Generation • 3B • Updated Feb 24, 2025 • 26
ilukashin/Qwen3-Coder-30B-A3B-Instruct-oQ4-fp16

31B • Updated May 20 • 166 • 1
ilukashin/Qwen3-Coder-30B-A3B-Instruct-oQ3.5-fp16

31B • Updated May 23 • 310
z-lab/Qwen3-Coder-30B-A3B-DFlash

Text Generation • 0.5B • Updated Apr 7 • 824 • 35

CyberNeurova × Qwen Family

Abliterations based on the Qwen model family. Includes vision-language variants and future Qwen2/Qwen3 text-only releases.

cyberneurova/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated May 20 • 56 • 5
cyberneurova/CyberNeurova-Qwen3.6-35B-A3B-abliterated

Text Generation • 35B • Updated May 20 • 77 • • 7
cyberneurova/cyberneurova-Qwen3.8-27B

Text Generation • 28B • Updated about 1 month ago • 199 • 2
cyberneurova/cyberneurova-Qwen3.8-27B-GGUF

Text Generation • 27B • Updated Aug 15 • 1.3k

ideogram-ai/ideogram-4-nf4

Text-to-Image • 5B • Updated Jun 4 • 2.18k • 501
ideogram-ai/ideogram-4-fp8

Text-to-Image • 9B • Updated Jun 3 • 51.9k • • 838
Running on Zero

Agents

Featured

255

Ideogram 4

🎨

255

Ideogram 4 state of the art open weights
ideogram-ai/ideogram-4-nf4-diffusers

Text-to-Image • 5B • Updated Jun 4 • 1.31k • 42

Google/Gemma4-E2B

Gemma 4 E2B Family Pure GGUFs

Smoffyy/Gemma4-E2B-Instruct-Pure-GGUF

Image-Text-to-Text • 5B • Updated Jun 6 • 441 • 1

Continual learning

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published May 19 • 89
OpenComputer: Verifiable Software Worlds for Computer-Use Agents

Paper • 2605.19769 • Published May 19 • 67
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

Paper • 2605.10912 • Published May 11 • 37
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

Paper • 2605.13941 • Published May 13 • 15

CyberNeurova Abliterations

Refusal-direction ablation across model families: text LLMs, VLMs, and unified multimodal generation. Full benchmarks + methodology per release.

cyberneurova/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated May 20 • 56 • 5
cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF

Text Generation • 284B • Updated May 6 • 3.93k • 62
cyberneurova/CyberNeurova-Lance-3B-abliterated

Any-to-Any • Updated May 20 • 8
cyberneurova/CyberNeurova-Qwen3.6-35B-A3B-abliterated

Text Generation • 35B • Updated May 20 • 77 • • 7

Music Source Separation Toolkit 2026

Open-source models + our reproducible MUSDB18-HQ benchmark for music source separation. Curated by the StemSplit team.

StemSplitio/stem-separation-benchmark-2026

Viewer • Updated May 19 • 850 • 60 • 1
Politrees/UVR_resources

Updated Dec 23, 2025 • 60
anvuew/BS-RoFormer

Updated Apr 17 • 359 • 11
anvuew/dereverb_bs_roformer

Updated Feb 13 • 631 • 24

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 20
ISTA-DASLab/Kimi-K2.6-2Bit-GSQ

Image-Text-to-Text • 84B • Updated Jun 17 • 281 • 6
ISTA-DASLab/Kimi-K2.5-2Bit-GSQ

Image-Text-to-Text • 84B • Updated Jun 17 • 494 • 1
ISTA-DASLab/Llama-3.1-70B-Instruct-2Bit-GSQ

Text Generation • 7B • Updated May 18 • 131 • 2

wnxsa/ada_atilgan

Updated May 30
wnxsa/ezgi_akliman

Updated May 29
wnxsa/buse_ortakci

Updated Jun 6
wnxsa/buse_balkan

Updated Jun 25

Google/Gemma4-E2B

Gemma 4 E2B Family Pure GGUFs

Smoffyy/Gemma4-E2B-Instruct-Pure-GGUF

Image-Text-to-Text • 5B • Updated Jun 6 • 441 • 1

Collection of artifacts for "SynthTools: A Framework for Scaling Synthetic Tools for Agent Development"

Continual learning

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published May 19 • 89
OpenComputer: Verifiable Software Worlds for Computer-Use Agents

Paper • 2605.19769 • Published May 19 • 67
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

Paper • 2605.10912 • Published May 11 • 37
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

Paper • 2605.13941 • Published May 13 • 15

Awesome Apple M1 Pro 32Gb local LLMs collection

Hardware: Apple Macbook Pro 14', M1 Pro chip 32Gb 14GPU. Clients: VS Code + Continue + Zoo Code (ex. Roo Code). Local LLM provider: oMLX.

alexgusevski/Qwen2.5-Coder-3B-Instruct-q6-mlx

Text Generation • 3B • Updated Feb 24, 2025 • 26
ilukashin/Qwen3-Coder-30B-A3B-Instruct-oQ4-fp16

31B • Updated May 20 • 166 • 1
ilukashin/Qwen3-Coder-30B-A3B-Instruct-oQ3.5-fp16

31B • Updated May 23 • 310
z-lab/Qwen3-Coder-30B-A3B-DFlash

Text Generation • 0.5B • Updated Apr 7 • 824 • 35

CyberNeurova Abliterations

Refusal-direction ablation across model families: text LLMs, VLMs, and unified multimodal generation. Full benchmarks + methodology per release.

cyberneurova/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated May 20 • 56 • 5
cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF

Text Generation • 284B • Updated May 6 • 3.93k • 62
cyberneurova/CyberNeurova-Lance-3B-abliterated

Any-to-Any • Updated May 20 • 8
cyberneurova/CyberNeurova-Qwen3.6-35B-A3B-abliterated

Text Generation • 35B • Updated May 20 • 77 • • 7

CyberNeurova × Qwen Family

Abliterations based on the Qwen model family. Includes vision-language variants and future Qwen2/Qwen3 text-only releases.

cyberneurova/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated May 20 • 56 • 5
cyberneurova/CyberNeurova-Qwen3.6-35B-A3B-abliterated

Text Generation • 35B • Updated May 20 • 77 • • 7
cyberneurova/cyberneurova-Qwen3.8-27B

Text Generation • 28B • Updated about 1 month ago • 199 • 2
cyberneurova/cyberneurova-Qwen3.8-27B-GGUF

Text Generation • 27B • Updated Aug 15 • 1.3k

Music Source Separation Toolkit 2026

Open-source models + our reproducible MUSDB18-HQ benchmark for music source separation. Curated by the StemSplit team.

StemSplitio/stem-separation-benchmark-2026

Viewer • Updated May 19 • 850 • 60 • 1
Politrees/UVR_resources

Updated Dec 23, 2025 • 60
anvuew/BS-RoFormer

Updated Apr 17 • 359 • 11
anvuew/dereverb_bs_roformer

Updated Feb 13 • 631 • 24

ideogram-ai/ideogram-4-nf4

Text-to-Image • 5B • Updated Jun 4 • 2.18k • 501
ideogram-ai/ideogram-4-fp8

Text-to-Image • 9B • Updated Jun 3 • 51.9k • • 838
Running on Zero

Agents

Featured

255

Ideogram 4

🎨

255

Ideogram 4 state of the art open weights
ideogram-ai/ideogram-4-nf4-diffusers

Text-to-Image • 5B • Updated Jun 4 • 1.31k • 42

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 20
ISTA-DASLab/Kimi-K2.6-2Bit-GSQ

Image-Text-to-Text • 84B • Updated Jun 17 • 281 • 6
ISTA-DASLab/Kimi-K2.5-2Bit-GSQ

Image-Text-to-Text • 84B • Updated Jun 17 • 494 • 1
ISTA-DASLab/Llama-3.1-70B-Instruct-2Bit-GSQ

Text Generation • 7B • Updated May 18 • 131 • 2

Previous
1
...
35
36
37
38
39
...
23,814
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs