# Qwen3.6-35B-A3B Q4_K_M Ryzen AI Max+ 395-ի վրա (llama.cpp Vulkan) — time to the first token of any output: 221 մվ

Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified համակարգի վրա, llama.cpp (server, Vulkan backend), b9049 (server_fingerprint b9049-2496f9c14) runtime-ով և ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M) մոդելով չափված «time to the first token of any output» մեծությունը կազմել է 221 մվ (median over all valid requests of three cells)։ Չափումը կատարվել է interactive-assistant-v1@2026-08-02 սառեցված workload-ի տակ; ապացույցի մակարդակը՝ lab_repeated, 9 վավեր գործարկում 1 ֆիզիկական յունիթի վրա։ Արժեքը վերաստացվում է գործարկումների հում գրառումներից ամեն CI build-ում։

## Statement

> On the tested Strix Halo configuration, the first streamed token of any kind arrives in a median of this many milliseconds — but on this model that first token is reasoning, not the answer.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.qwen36.interactive.c1.ttft-any-token` |
| Value | 221 ms |
| Metric | time to the first token of any output |
| Aggregation | median over all valid requests of three cells |
| 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-v1@2026-08-02 |
| Evidence level | lab_repeated |
| Status | active |
| Runs | 9 across 1 unit(s) |
| Published | 2026-08-02 |
| Last changed | 2026-08-02 |

**Limitations.** Nine runs across three cells on one unit — repeated, not unit-replicated. Measured at concurrency 1 on a quiesced node with a desktop session present. Says nothing about when a usable answer starts; see the answer-token claim.

## Raw evidence

- Sealed run bundle `run-20260802-nothink-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-nothink-a
- Sealed run bundle `run-20260802-nothink-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-nothink-a-r2
- Sealed run bundle `run-20260802-nothink-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-nothink-a-r3
- Sealed run bundle `run-20260802-budget4k-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-budget4k-a
- Sealed run bundle `run-20260802-budget4k-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-budget4k-a-r2
- Sealed run bundle `run-20260802-budget4k-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-budget4k-a-r3
- Sealed run bundle `run-20260802-gonogo-a2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-gonogo-a2
- Sealed run bundle `run-20260802-budget1k-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-budget1k-a-r2
- Sealed run bundle `run-20260802-budget1k-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260802-budget1k-a-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttft-any-token.sql
- Machine-readable: https://agmind.ai/claims/strix.qwen36.interactive.c1.ttft-any-token.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/hy/reports/ttft-thinking-model-strix-halo/
- https://agmind.ai/hy/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 the first token of any output — 221 ms (median over all valid requests of three cells; 9 runs on 1 unit; evidence level lab_repeated; workload interactive-assistant-v1@2026-08-02). Claim strix.qwen36.interactive.c1.ttft-any-token. https://agmind.ai/claims/strix.qwen36.interactive.c1.ttft-any-token/

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/hy/claims/strix.qwen36.interactive.c1.ttft-any-token/