Qwen3.8 27B
on TPU v5e-8 · 262,144 ctx
Summary
User reports Qwen3.8-27B in bf16 on Kaggle's free TPU v5e-8 at about 130 t/s generation with MTP and about 78 t/s without, plus 10,300 t/s prefill.
The full 262k context is supported, and the user serves an OpenAI-compatible endpoint through a Cloudflare tunnel.