Strix Halo (gorgon-halo) DwarfStar ROCm 10.0 DeepSeek-V4.1-Flash Q2 64k-depth decode

Protocol deterministic-prime-extend-completions-v1, runner local-llm-speed v1, measured at the OpenAI-completions API endpoint. Mean of 2 repeats after 1 warmup. Concurrency 1, so the figure is per-request, not aggregate. Depth is the primed KV prefix; at depth 0 the whole prompt is computed (actual cached depth 0, recomputed history 0). Prefill is effective follow-up prompt processing: uncached tokens divided by client-observed time to first output. Decode is client-observed generation throughput over the tokens after the first, so TTFT is excluded. KV cache type default, speculative decoding off. Source: local-llm-benchmarks.dev/data/results.json. Run run-6fc53c1202e61fc0, completed 2026-09-30. Engine DwarfStar 51ed19af418bc13fc825887198799533493916672af78010bbb2642ec5fa6211 /usr/local/bin/ds4-server, runtime ROCm 10.0. Container docker.io/kyuz0/strix-halo-ds4-toolbox:rocm-10.0. Weights: antirez/deepseek-v4.1-flash-gguf file DeepSeek-V4.1-Flash-Q2.gguf, quant Q2. Prompt 2048 tokens, 256 generated, primed depth 65536.

Decode holds nearly flat from depth 0 (14.76) to 65536. Prefill falls from 240.86 to 140.91 tok/s.