# Qwen3.6-35B-A3B Q4_K_M на Ryzen AI Max+ 395 (llama.cpp Vulkan) — time to first token, first question over a 32k document: 33940 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 «time to first token, first question over a 32k document» составила 33940 мс (median over valid requests for this item). Измерение выполнено под замороженным ворклоадом doc-session-v1@2026-08-03; уровень доказательности — lab_repeated, 3 валидных прогонов на 1 физическом(-их) юните(-ах). Значение перевыводится из сырых записей прогонов на каждом CI-билде.

## Statement

> Median time to first token for the FIRST question over a 32k-token English document — the prefill every fresh document pays, prompt cache enabled.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.qwen36.docsession.c1.ttft-q1-32k` |
| Value | 33940 ms |
| Metric | time to first token, first question over a 32k document |
| Aggregation | median over valid requests for this item |
| 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 | doc-session-v1@2026-08-03 |
| Evidence level | lab_repeated |
| Status | active |
| Runs | 3 across 1 unit(s) |
| Published | 2026-08-03 |
| Last changed | 2026-08-03 |

**Limitations.** Three repeated runs on one unit, reasoning disabled, single stream. Cache benefit requires a byte-identical document prefix in the same server session.

## Raw evidence

- Sealed run bundle `run-20260803-ds-cache-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-ds-cache-a
- Sealed run bundle `run-20260803-ds-cache-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-ds-cache-a-r2
- Sealed run bundle `run-20260803-ds-cache-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-ds-cache-a-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttft-ds-en-32k-q1.sql
- Machine-readable: https://agmind.ai/claims/strix.qwen36.docsession.c1.ttft-q1-32k.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/ru/reports/llamacpp-prompt-cache-strix-halo/
- https://agmind.ai/ru/tested-configurations/strix-halo-qwen36-llamacpp-vulkan-docsession/
- https://agmind.ai/ru/compare/prompt-cache-on-vs-off-doc-session/
- 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): time to first token, first question over a 32k document — 33940 ms (median over valid requests for this item; 3 runs on 1 unit; evidence level lab_repeated; workload doc-session-v1@2026-08-03). Claim strix.qwen36.docsession.c1.ttft-q1-32k. https://agmind.ai/claims/strix.qwen36.docsession.c1.ttft-q1-32k/

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.docsession.c1.ttft-q1-32k/