Home SOC: One Report on the Radeon GPU

Name: Home SOC: One Report on the Radeon GPU
Creator: Trevor Unland
Published: 2026-10-28
License: https://github.com/TrevTron/protectli-home-soc/blob/main/LICENSE

One live report ran on the Minisforum's Radeon 8060S. The runner confirmed all 33 model layers were offloaded, and the returned report passed the existing checker.

This page keeps the shared controls, retained measurements, failures, and comparison limits together. The linked files are there when you need the underlying table or method.

What you can compare here

The 20.781 seconds is the total HTTP request duration for one report with 309 generated tokens. The input and answer length differ from the CPU study. Use this as evidence that GPU execution worked, not a CPU/GPU speed comparison.

Read the article Project repository

You can reuse Trevor-measured data from this page under the repository MIT terms. Retain the required notices when reusing the project documentation, and credit Trevor Unland when citing this run. Project media has separate terms in the repository.

Recorded results

Open the details under any row for the specific setup, outcome, artifact identity, and supporting file.

Qwen3.5 4B

First live GPU acceptance

Partial result

Measured on Minisforum MS-S1 MAX · Vulkan / Radeon 8060S

HTTP report duration: 20.781 seconds; One live request; includes more than token generation
Actual generated tokens: 309 tokens; Returned request receipt
Offloaded layers: 33 layers; Actual runner identified Radeon 8060S; 33 of 33 layers

The structured report passed validation, but some explanation remained generic. No matched speedup or generation-rate claim.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · Vulkan / Radeon 8060S · First live GPU acceptance

Context window: 4,096 tokens for input and output together. CPU-thread setting: 2; this is a runtime setting, not the host's core count.

Installed artifact digest: d8b0f5e9760cd1682034f292d7ef72ec46f432149be0df7574bf2d6e92e38c04

Results and method Actual test host

Supporting evidence

Results and method

These are the few files that support this page directly. The repository holds the wider project history.

GPU deployment evidence Actual offload, deployment boundaries, live acceptance and host availability.

Controls

SOC-only runtime and model store; Vulkan; one parallel request; keepalive zero
Qwen3.5 4B Q4_K_M; actual runner log identifies Radeon 8060S and 33/33 offloaded layers
Common generation profile; thinking disabled; retained resource/deadline/source guards

What this run established

$Report completed in 20.781 seconds with 309 actual generated tokens and passed the brief validator.
$Some context and next checks remained generic. Validation did not establish complete investigation usefulness.
$GPU acceptance is separate from historical CPU-model comparisons.