Qwen3.8 27B
on NVIDIA RTX 5090 · Ollama · 65,536 ctx
Oct 1, 2026
Summary
User benchmarks Qwen3.8-27B at 171 tok/s on an RTX 5090, solving 14 of 16 hard problems.
Setup is Ollama with Q4_K_M GGUF at 64K context, temperature 0.2 and a 32,768-token generation cap, using 17.5 GB of VRAM.
Nemotron 3.5 Lightning reached 216 tok/s and 14/16 at 25.4 GB, while Muse Glimmer reached 81 tok/s and 15/16 at 16.9 GB.