Qwen3.8 Flash CIRU Orca v5.0, uncached 256000-token prefill

on AMD Strix Halo 128GB · CIRU v5 native HIP · 262,144 ctx

Oct 11, 2026

Throughput

1003.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

CIRU v5 compact indexed affine (experts 4.5175 bpw) (GGUF)

KV cache

F16

MTP (Multi-Token Prediction)

System RAM

128 GB

Use cases

long-context

Summary

User reports Qwen3.8-Flash-CIRU-STRIX-Orca v5.0 at 1003 t/s prompt processing on one AMD Ryzen AI Max+ 395 / Radeon 8060S system with 128 GiB shared unified memory. Setup is CIRU v5 native HIP with the compact indexed-affine expert format at 4.5175 bpw, a 262144-token configured context, 16384 batch and microbatch, F16 target and draft attention cache, and a Q8 Orca MTP drafter at depth 4. The figure is a full-prefix prefill of 256000 tokens from zero cached prefix, not the later 2048-token cached append and not TTFT; one initial observation, no repeats.