# Qwen3.6-35B-A3B Q4_K_M Ryzen AI Max+ 395-ի վրա (llama.cpp Vulkan) — time to first token at a 2k-token document: 1907 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 first token at a 2k-token document» մեծությունը կազմել է 1907 մվ (median over valid 2k-band requests)։ Չափումը կատարվել է long-context-v1@2026-08-03 սառեցված workload-ի տակ; ապացույցի մակարդակը՝ lab_repeated, 3 վավեր գործարկում 1 ֆիզիկական յունիթի վրա։ Արժեքը վերաստացվում է գործարկումների հում գրառումներից ամեն CI build-ում։

## Statement

> Median client-side time to the first token when the prompt carries a 2k-token English document.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.qwen36.longctx.c1.ttft-2k-en` |
| Value | 1907 ms |
| Metric | time to first token at a 2k-token document |
| Aggregation | median over valid 2k-band 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 | long-context-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. Synthetic needle retrieval at a fixed ~50% depth — not comprehension; tested to 32k tokens, no claim beyond.

## Raw evidence

- Sealed run bundle `run-20260803-lc-nothink-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-lc-nothink-a
- Sealed run bundle `run-20260803-lc-nothink-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-lc-nothink-a-r2
- Sealed run bundle `run-20260803-lc-nothink-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-lc-nothink-a-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/ttft-ctx2k-en.sql
- Machine-readable: https://agmind.ai/claims/strix.qwen36.longctx.c1.ttft-2k-en.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/hy/tested-configurations/strix-halo-qwen36-llamacpp-vulkan-longcontext/
- https://agmind.ai/hy/compare/context-2k-vs-32k-qwen36-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 first token at a 2k-token document — 1907 ms (median over valid 2k-band requests; 3 runs on 1 unit; evidence level lab_repeated; workload long-context-v1@2026-08-03). Claim strix.qwen36.longctx.c1.ttft-2k-en. https://agmind.ai/claims/strix.qwen36.longctx.c1.ttft-2k-en/

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.longctx.c1.ttft-2k-en/