alt
Hacker News
banditelol
•
yesterday at 5:05 PM
•
1 reply
•
view on HN
what model you used with llama_cpp?
Replies
zkmon
•
yesterday at 5:38 PM
Qwen3.6-35B quant-4 gguf
alt Hacker News
Qwen3.6-35B quant-4 gguf