Qwen3.8 125B (6B active) Flash-Next
AMD RX 9060 XT 16GB · Strata · 65,536 ctx
- generation:
- 45.5 tokens/s
- prompt processing (prefill):
- 161.9 tokens/s
- quant:
- Q2_0 (GGUF)
- kv:
- int8
User reports Qwen3.8-Flash-Next Q2_0 at 45.5 t/s decode and 161.9 t/s prefill (pp4k) on an RX 9060 XT 16GB with 32GB DDR4, but says prefill is usually under 150 t/s and asks how to fix it. Setup is Strata 0.1.52 (HIP backend, Windows) with a 64K context and int8 KV cache; the 37.6 GB GGUF exceeds the card's VRAM, so weights run partly from system RAM. Strata's tuner ran 501.5 s and confirmed the defaults; two tuning arms were skipped for lack of free memory (25.6 GiB free, 28.4 GiB needed).