# gemma-4-26B-A4B-it Q4_0 на Ryzen AI Max+ 395 (llama.cpp Vulkan) — strict-JSON task success: 93.8 % запросов

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/gemma-4-26B-A4B-it-GGUF @ bb4531cda34d (Q4_0) измеренная величина «strict-JSON task success» составила 93.8 % запросов (share of all issued requests). Измерение выполнено под замороженным ворклоадом structured-agent-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

> Share of strict-JSON automation requests whose output parsed and matched the ground truth per key, default operating mode.

## Evidence

| Field | Value |
| --- | --- |
| Claim id | `strix.gemma4.structured.c1.task-success` |
| Value | 93.8 % of requests |
| Metric | strict-JSON task success |
| Aggregation | share of all issued 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/gemma-4-26B-A4B-it-GGUF @ bb4531cda34d (Q4_0) |
| Workload scope | structured-agent-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. Default operating mode of the model (reasoning emitted); disabling reasoning via the chat template was not tested for this model family. Failures were unparseable outputs on RU generation tasks, not wrong values.

## Raw evidence

- Sealed run bundle `run-20260803-gm-sa-a`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-gm-sa-a
- Sealed run bundle `run-20260803-gm-sa-a-r2`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-gm-sa-a-r2
- Sealed run bundle `run-20260803-gm-sa-a-r3`: https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-gm-sa-a-r3
- Derivation query: https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/json-task-success.sql
- Machine-readable: https://agmind.ai/claims/strix.gemma4.structured.c1.task-success.json · full registry https://agmind.ai/claims.json

## Cited on

- https://agmind.ai/ru/reports/model-quant-backend-strix-halo/
- https://agmind.ai/ru/reports/local-llm-json-reliability/
- https://agmind.ai/ru/measured/gemma-4-26b-a4b-it-q4-0-on-ryzen-ai-max-395/

## Cite this

AGmind Systems Lab. gemma-4-26B-A4B-it Q4_0 on Ryzen AI Max+ 395 (llama.cpp Vulkan): strict-JSON task success — 93.8 % of requests (share of all issued requests; 3 runs on 1 unit; evidence level lab_repeated; workload structured-agent-v1@2026-08-03). Claim strix.gemma4.structured.c1.task-success. https://agmind.ai/claims/strix.gemma4.structured.c1.task-success/

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.gemma4.structured.c1.task-success/