cached 64K + 2048 input, 512 output

on AMD Radeon 8060S / gfx1151 (Strix Halo; 128 GiB unified-memory class) · Halogen · 262,144 ctx

Oct 13, 2026

Throughput

56.9 t/s gen · 1196.5 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

W4B + default quality overlay

MTP (Multi-Token Prediction)

Summary

User reports Qwen3.8 at 56.9 t/s generation and 1196.5 t/s prompt processing on an AMD Radeon 8060S / gfx1151 host with 128 GiB unified memory. Setup is Halogen 0.14.2 with W4B plus default quality overlay, native MTP, one KV slot and 262144 configured positions on one render device. The headline is a warm cached-prefix result at 64000 cached depth with 2048 new tokens (66048 total input) and 512 outputs; the preceding 45.17 s prefix refresh and model load are excluded, and the source-normalized rate for this cell is 56.75318 t/s.