Qwen3.8
on Unknown GPU · llama.cpp · 262,144 ctx
Use cases
coding
Summary
User reports Qwen3.8 generation dropping from around 10 t/s to 2.8 t/s after 8 hours on a Rust coding task.
Setup is llama.cpp compiled in f16 mode with the maximum context size of 262k tokens, restricted to a single GPU, driven through opencode.
User asks why throughput degrades over a long session and whether it can be fixed.