Measured

gemma-4-26B-A4B-it Q4_0 on Ryzen AI Max+ 395 — every measured number

Everything this lab has measured for gemma-4-26B-A4B-it Q4_0 on Ryzen AI Max+ 395: 6 claims across 3 frozen workloads, backends llama.cpp Vulkan. Each number links to its permanent claim page with scope, limitations and sealed run evidence — values are re-derived from raw records in CI.

interactive-assistant-v2@2026-08-02

Metric Value Evidence Claim
answerless (empty) responses in default mode · llama.cpp Vulkan 8.3 % of requests lab_repeated strix.gemma4.interactive2.c1.answerless-default
time to first answer token in default mode · llama.cpp Vulkan 10768 ms lab_repeated strix.gemma4.interactive2.c1.ttfa-default
time to the first token of any output · llama.cpp Vulkan 282 ms lab_repeated strix.gemma4.interactive2.c1.ttft-any-token

long-context-v1@2026-08-03

Metric Value Evidence Claim
unanswerable-control honesty · llama.cpp Vulkan 75.0 % of requests lab_repeated strix.gemma4.longctx.c1.control-success
needle retrieval success · llama.cpp Vulkan 95.8 % of requests lab_repeated strix.gemma4.longctx.c1.needle-success

structured-agent-v1@2026-08-03

Metric Value Evidence Claim
strict-JSON task success · llama.cpp Vulkan 93.8 % of requests lab_repeated strix.gemma4.structured.c1.task-success

How to read this page

These are scoped measurements, not a ranking. A verdict for a workload lives on its tested-configuration card; a number without its limitations is not comparable across systems. Statements are EN-canonical on the claim pages.

Start here: /tested-configurations/ /compare/ /claims/