# Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan) — time to first token, second question with prompt cache off: 33728 ms

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 token, second question with prompt cache off was 33728 ms (median over valid requests for this item). The measurement was taken under the frozen doc-session-v1@2026-08-03 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.

## Statement

> Median time to first token for the second question over the same 32k-token document with the prompt cache disabled — the full prefill is paid again.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.qwen36.docsession.c1.ttft-q2-32k-nocache` |
| Value | 33728 ms |
| Metric | time to first token, second question with prompt cache off |
| 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.

## Raw evidence

- Sealed run bundle `run-20260803-ds-nocache-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-ds-nocache-a
- Sealed run bundle `run-20260803-ds-nocache-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-ds-nocache-a-r2
- Sealed run bundle `run-20260803-ds-nocache-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-ds-nocache-a-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttft-ds-en-32k-q2.sql
- Machine-readable: https://agmind.ai/claims/strix.qwen36.docsession.c1.ttft-q2-32k-nocache.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/reports/llamacpp-prompt-cache-strix-halo/
- https://agmind.ai/tested-configurations/strix-halo-qwen36-llamacpp-vulkan-docsession/
- https://agmind.ai/compare/prompt-cache-on-vs-off-doc-session/
- https://agmind.ai/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, second question with prompt cache off — 33728 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-q2-32k-nocache. https://agmind.ai/claims/strix.qwen36.docsession.c1.ttft-q2-32k-nocache/

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/claims/strix.qwen36.docsession.c1.ttft-q2-32k-nocache/