{
 "attribution": "AGmind Systems Lab (agmind.ai)",
 "id": "strix.qwen36.interactive2.c8.ttfa-p95-nothink",
 "headline": "Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan) — time to first answer token, 95th percentile, 8 concurrent requests: 1088 ms",
 "answer": "On a Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified running llama.cpp (server, Vulkan backend), b9049 (server_fingerprint b9049-2496f9c14) with ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M), the measured time to first answer token, 95th percentile, 8 concurrent requests was 1088 ms (95th percentile over valid requests, interpolated). 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": "1088",
 "unit": "ms",
 "metric": "time to first answer token, 95th percentile",
 "concurrency": 8,
 "system": "Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified",
 "runtime": "llama.cpp (server, Vulkan backend), b9049 (server_fingerprint b9049-2496f9c14)",
 "model": "ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M)",
 "units_measured": 1,
 "statement": "95th-percentile client-side time to the first answer token with the reasoning block disabled, while 8 closed-loop streams run concurrently on the unit (each request measured from its own client) — the slow tail of the same requests behind the median claim.",
 "scope": "interactive-assistant-v2@2026-08-02",
 "aggregation": "95th percentile over valid requests, interpolated",
 "limitations": "Three repeated runs on one unit. Closed-loop concurrency 8 — not an arrival-rate/SLO capacity claim. Context split across server slots (8192 per slot). Each run has 16 corpus items, so even pooled across the listed runs the 95th percentile rests on a handful of the slowest requests — a coarse tail statistic, not a tail-latency model. Failed requests carry no answer-token time and are outside this statistic; the completion-share claim on the same runs accounts for them.",
 "evidence_level": "lab_repeated",
 "status": "active",
 "published": "2026-09-02",
 "last_changed": "2026-09-02",
 "run_ids": [
  "run-20260803-v2-c8-nothink-a",
  "run-20260803-v2-c8-nothink-a-r2",
  "run-20260803-v2-c8-nothink-a-r3"
 ],
 "runs": [
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-c8-nothink-a",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-c8-nothink-a-r2",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-c8-nothink-a-r3"
 ],
 "derivation_sql": "https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttfa-p95-nothink.sql",
 "permalink": "https://agmind.ai/claims/strix.qwen36.interactive2.c8.ttfa-p95-nothink/",
 "cited_on": [
  "https://agmind.ai/measured/qwen3-6-35b-a3b-q4-k-m-on-ryzen-ai-max-395/"
 ],
 "json": "https://agmind.ai/claims/strix.qwen36.interactive2.c8.ttfa-p95-nothink.json",
 "markdown": "https://agmind.ai/claims/strix.qwen36.interactive2.c8.ttfa-p95-nothink.md",
 "quote": "Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan): time to first answer token, 95th percentile, 8 concurrent requests — 1088 ms (95th percentile over valid requests, interpolated; 3 runs on 1 unit; evidence level lab_repeated; workload interactive-assistant-v2@2026-08-02).",
 "cite": "AGmind Systems Lab. Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan): time to first answer token, 95th percentile, 8 concurrent requests — 1088 ms (95th percentile over valid requests, interpolated; 3 runs on 1 unit; evidence level lab_repeated; workload interactive-assistant-v2@2026-08-02). Claim strix.qwen36.interactive2.c8.ttfa-p95-nothink. https://agmind.ai/claims/strix.qwen36.interactive2.c8.ttfa-p95-nothink/",
 "changes_feed": "https://agmind.ai/claims/changes.xml",
 "license": "https://creativecommons.org/licenses/by/4.0/",
 "corrections": "https://agmind.ai/errata/"
}