Thread

1. fsiefken · 1791127208 · focus · HN ↗

   I wonder if a higher Qwen3.8-27b quant could beat or match these lower < 16/24/48/64G Qwen3.8-Flash Next quants given similar quality.

   What speed are you willing the sacrifice to debug/program for more complex jobs faster?

   Then there are also these quants; <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;IsValorum&#x2F;Qwen3.8-35B-A3B-Distill-MLX-APEX-NanoPlus-Abliterated" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;IsValorum&#x2F;Qwen3.8-35B-A3B-Distill-MLX...

   1. happycube · 1791143521 · focus · HN ↗

      Maybe, but those higher quants would need a large GPU accessible memory space - and the obvious candidates such as DGX Spark and Strix Halo don&#x27;t have the bandwidth to run 27B at high quality quickly.

      With Flash Next you only have ~6B active parameters so you can toss experts up into VRAM and&#x2F;or run them on a CPU if you have enough RAM and bandwidth.

Unofficial Hacker News client; not affiliated with Y Combinator.