🤝 Open to Collab

CYGDEN

CYGDEN

·

HTTPS://T.ME/OOUSN

AI & ML interests

⠀

Recent Activity

liked a model 10 days ago

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

liked a model 10 days ago

zai-org/GLM-5.3

liked a model 10 days ago

XHToken/Spark-X2.5-4B

View all activity

Organizations

None yet

liked 3 models 10 days ago

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Image-Text-to-Text • 305B • Updated 15 days ago • 634k • • 912

zai-org/GLM-5.3

Text Generation • 753B • Updated 12 days ago • 801k • • 1.84k

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated 1 day ago • 27.2k • 1.23k

liked 5 models about 1 month ago

CohereLabs/North-Micro-Vision-Instruct

Image-Text-to-Text • 2B • Updated 5 days ago • 133k • 142

LiquidAI/LFM2.5-2.6B

Text Generation • 3B • Updated 23 days ago • 91.7k • 762

MiniMaxAI/MiniMax-Music3

Text-to-Audio • 2B • Updated Aug 14 • 16.7k • 1.39k

meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated Aug 11 • 379k • • 1.9k

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 7.67M • • 15.3k

liked 10 models about 2 months ago

thinkingmachines/Inkling-Small

Image-Text-to-Text • 266B • Updated Jul 31 • 474k • • 406

krea/Krea-2-Turbo

Text-to-Image • 13B • Updated Jul 24 • 73.6k • • 1.25k

Qwen/Qwen3.6-27B

Image-Text-to-Text • 28B • Updated Apr 24 • 3.89M • • 2.3k

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 291B • Updated Jun 22 • 1.7M • • 2.23k

amd/Instella-MoE-16B-A3B-Think

Text Generation • 16B • Updated 14 days ago • 2.83k • 178

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated about 10 hours ago • 1.33M • 676

microsoft/Fara1.5-27B

Image-Text-to-Text • 27B • Updated Jul 27 • 1.78k • • 290

upstage/Solar-Open2-250B

Text Generation • 250B • Updated Jul 31 • 10.5k • 754

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated Jul 29 • 2.38M • 4.26k

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 14 days ago • 2.24M • • 11.4k

reacted to danielhanchen's post with ❤️👍 about 2 months ago

Post

4714

Kimi K3 can now be run locally! ✨

The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).

Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.

GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3

5 replies

·