# Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan) — time to first answer token with reasoning on: 20191 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 answer token with reasoning on was 20191 ms (median over valid requests). The measurement was taken under the frozen interactive-assistant-v2@2026-08-02 workload; evidence level lab_unit_replicated, 6 valid runs across 2 physical units. The value is re-derived from the raw run records on every CI build.

## Statement

> Median client-side time to the first token of the actual answer with reasoning enabled at a 4096-token budget, human-task corpus.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.qwen36.interactive2.c1.ttfa-thinking` |
| Value | 20191 ms |
| Metric | time to first answer token with reasoning on |
| Aggregation | median over valid requests |
| 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 | 2026-08-03 |
| Last changed | 2026-08-03 |

**Limitations.** Three repeated runs across two commercially identical units — diagnostic depth, not a cross-unit qualification.

## Raw evidence

- Sealed run bundle `run-20260802-v2-budget4k-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-v2-budget4k-a
- Sealed run bundle `run-20260802-v2-budget4k-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-v2-budget4k-a-r2
- Sealed run bundle `run-20260802-v2-budget4k-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-v2-budget4k-a-r3
- Sealed run bundle `run-20260803-v2-budget4k-b`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-budget4k-b
- Sealed run bundle `run-20260803-v2-budget4k-b-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-budget4k-b-r2
- Sealed run bundle `run-20260803-v2-budget4k-b-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-v2-budget4k-b-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttfa-thinking-1k.sql
- Machine-readable: https://agmind.ai/claims/strix.qwen36.interactive2.c1.ttfa-thinking.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/reports/how-many-tokens-per-second-is-enough/
- https://agmind.ai/reports/should-you-disable-thinking-local-llm/
- https://agmind.ai/tested-configurations/strix-halo-qwen36-llamacpp-vulkan-interactive/
- https://agmind.ai/compare/gemma4-vs-qwen36-answerless/
- https://agmind.ai/compare/thinking-vs-no-thinking-qwen36/
- 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 answer token with reasoning on — 20191 ms (median over valid requests; 6 runs on 2 units; evidence level lab_unit_replicated; workload interactive-assistant-v2@2026-08-02). Claim strix.qwen36.interactive2.c1.ttfa-thinking. https://agmind.ai/claims/strix.qwen36.interactive2.c1.ttfa-thinking/

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.interactive2.c1.ttfa-thinking/