Qwen3.8 27B
on NVIDIA RTX 4070 Ti Super · llama.cpp · 4,096 ctx
Sep 7, 2026
Summary
User reports a 4070 Super run that was slow because only 38 of 66 layers were on GPU, with the rest running from system RAM.
The same model achieved 81.5 tok/s on a 5090.
The user introduces a tool called Picchio for diagnosing layer placement and speeds.