# Qwen3.6-35B-A3B Q4_K_M на Ryzen AI Max+ 395 (llama.cpp Vulkan) — run-to-run spread of the median time to first answer token: 11 мс

На системе Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified под управлением llama.cpp (server, Vulkan backend), b9049 (server_fingerprint b9049-2496f9c14) с моделью ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M) измеренная величина «run-to-run spread of the median time to first answer token» составила 11 мс (highest minus lowest per-run median over valid requests, across the listed runs). Измерение выполнено под замороженным ворклоадом interactive-assistant-v2@2026-08-02; уровень доказательности — lab_unit_replicated, 6 валидных прогонов на 2 физическом(-их) юните(-ах). Значение перевыводится из сырых записей прогонов на каждом CI-билде.

## Statement

> Spread between the per-run medians of client-side time to the first answer token, reasoning block disabled, across the listed runs and units: the highest run median minus the lowest. A repeatability indicator for this cell, not a variance model.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.qwen36.interactive2.c1.ttfa-nothink-spread` |
| Value | 11 ms |
| Metric | run-to-run spread of the median time to first answer token |
| Aggregation | highest minus lowest per-run median over valid requests, across the listed runs |
| 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 artifact | ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M) |
| Workload scope | interactive-assistant-v2@2026-08-02 |
| Evidence level | lab_unit_replicated |
| Status | active |
| Runs | 6 across 2 unit(s) |
| Published | 2026-09-02 |
| Last changed | 2026-09-02 |

**Limitations.** Three repeated runs across two commercially identical units — six per-run medians in total, so the spread is a range over a small sample, not a confidence interval. Pools unit-to-unit and repeat-to-repeat differences into one number; it does not separate the two. Each run has 16 corpus items, so a single per-run median moves with one or two requests.

## Raw evidence

- Sealed run bundle `run-20260802-v2-nothink-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-v2-nothink-a
- Sealed run bundle `run-20260802-v2-nothink-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-v2-nothink-a-r2
- Sealed run bundle `run-20260802-v2-nothink-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-v2-nothink-a-r3
- Sealed run bundle `run-20260803-v2-nothink-b`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-nothink-b
- Sealed run bundle `run-20260803-v2-nothink-b-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-nothink-b-r2
- Sealed run bundle `run-20260803-v2-nothink-b-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-nothink-b-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttfa-run-spread.sql
- Machine-readable: https://agmind.ai/claims/strix.qwen36.interactive2.c1.ttfa-nothink-spread.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/ru/measured/qwen3-6-35b-a3b-q4-k-m-on-ryzen-ai-max-395/

## Cite this

AGmind Systems Lab. Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan): run-to-run spread of the median time to first answer token — 11 ms (highest minus lowest per-run median over valid requests, across the listed runs; 6 runs on 2 units; evidence level lab_unit_replicated; workload interactive-assistant-v2@2026-08-02). Claim strix.qwen36.interactive2.c1.ttfa-nothink-spread. https://agmind.ai/claims/strix.qwen36.interactive2.c1.ttfa-nothink-spread/

Registry changes feed: https://agmind.ai/claims/changes.xml · Corrections to published results: https://agmind.ai/errata/ · Data licensed CC BY 4.0.
Source page: https://agmind.ai/ru/claims/strix.qwen36.interactive2.c1.ttfa-nothink-spread/