Hacker News new | ask | show | jobs
by sparacha 357 days ago
yes - we have already published a quantized version here: https://huggingface.co/katanemo/Arch-Router-1.5B.gguf. The performance difference with a quant version is negligible. I'll run another analysis and update the thread shortly
1 comments
sparacha 356 days ago
Overall performance degrades from 93.17 -> 92.99 with a quantized version
link