{
 "attribution": "AGmind Systems Lab (agmind.ai)",
 "id": "strix.qwen36q4.rocm.c1.itl-nothink",
 "headline": "Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp ROCm) — inter-token latency: 18.7 ms/token",
 "answer": "On a Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified running llama.cpp (server, ROCm backend), b9049 (server_fingerprint b9049-2496f9c14) with ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M), the measured inter-token latency was 18.7 ms/token (median over valid requests). The measurement was taken under the frozen interactive-assistant-v2@2026-08-02 workload; evidence level lab_repeated, 3 valid runs across 1 physical unit. The value is re-derived from the raw run records on every CI build.",
 "value": "18.7",
 "unit": "ms/token",
 "metric": "inter-token latency",
 "concurrency": 1,
 "system": "Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified",
 "runtime": "llama.cpp (server, ROCm backend), b9049 (server_fingerprint b9049-2496f9c14)",
 "model": "ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M)",
 "units_measured": 1,
 "statement": "Median inter-token latency (client-side decode-speed proxy) for Q4_K_M on the ROCm backend.",
 "scope": "interactive-assistant-v2@2026-08-02",
 "aggregation": "median over valid requests",
 "limitations": "Three repeated runs on one unit, reasoning disabled.",
 "evidence_level": "lab_repeated",
 "status": "active",
 "run_ids": [
  "run-20260803-rocm-v2-nothink-a",
  "run-20260803-rocm-v2-nothink-a-r2",
  "run-20260803-rocm-v2-nothink-a-r3"
 ],
 "runs": [
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-rocm-v2-nothink-a",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-rocm-v2-nothink-a-r2",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-rocm-v2-nothink-a-r3"
 ],
 "derivation_sql": "https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/itl-median.sql",
 "permalink": "https://agmind.ai/claims/strix.qwen36q4.rocm.c1.itl-nothink/",
 "json": "https://agmind.ai/claims/strix.qwen36q4.rocm.c1.itl-nothink.json",
 "markdown": "https://agmind.ai/claims/strix.qwen36q4.rocm.c1.itl-nothink.md",
 "cite": "AGmind Systems Lab. \"Median inter-token latency (client-side decode-speed proxy) for Q4_K_M on the ROCm backend.\" Claim strix.qwen36q4.rocm.c1.itl-nothink (18.7 ms/token), evidence level lab_repeated, scope interactive-assistant-v2@2026-08-02. https://agmind.ai/claims/strix.qwen36q4.rocm.c1.itl-nothink/",
 "license": "https://creativecommons.org/licenses/by/4.0/",
 "corrections": "https://agmind.ai/errata/"
}