Lilian

lilianmoraru

4

·

AI & ML interests

None yet

Recent Activity

new activity about 1 hour ago

unsloth/DeepSeek-V4-Flash-0731-GGUF:Lossless UD-Q8_K_XL. UD-Q4_K_XL also provided for now

new activity about 18 hours ago

unsloth/Kimi-K3-GGUF:1-bit Kimi K3 vs Claude Opus 5 vs GPT 5.6

reacted to danielhanchen's post with 👍 2 days ago

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

View all activity

Organizations

None yet

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 1 hour ago

Lossless UD-Q8_K_XL. UD-Q4_K_XL also provided for now

#2 opened about 2 hours ago by

New activity in unsloth/Kimi-K3-GGUF about 18 hours ago

1-bit Kimi K3 vs Claude Opus 5 vs GPT 5.6

#12 opened 2 days ago by

New activity in poolside/Laguna-S-2.1-NVFP4 3 days ago

Reproducible Laguna S 2.1 NVFP4 runaway reasoning: output budget scales 2K → 16K with 12/12 length exhaustion and no final answer

#16 opened 5 days ago by

New activity in poolside/Laguna-S-2.1-NVFP4 8 days ago

Not thinking even when `chat_template_kwargs` is set?

#13 opened 8 days ago by