/hub/models/qwen35-4b

Qwen3.5 · 4B

Qwen3.5 4B

I selected Qwen3.5 4B for the scheduled Home SOC report under the tested shared settings. Finishing a report, including the expected explanations and passing the full answer checklist are counted separately.

result records

Trevor-measured rows

test groups

devices represented

Why Qwen3.5 4B is in The Hub

Compared against the original 4B, 9B and Gemma on the same fixed briefs under bounded deadlines.

The rows on this page use Structured report; default sampling, Written report; default sampling, Simulation logs; default sampling, Structured report; shared sampling, Original V1 investigator, Intermediate V5; invalid condition comparison, Corrected V6 condition A: evidence only, Corrected V6 condition B: analyst assistance, Corrected V6 condition C: assistance plus grouping, and First live GPU acceptance through Ollama 0.35.1. They describe those exact artifacts and runs, not every version that shares the model name.

What the recorded rows show

This record contains an outcome without a numeric generation result.

2 retained rows are failures: Some answers copied real groups and then claimed there were no alerts; empty cases invented groups. Practice answers stayed outside the measured denominator. Two inputs were cut from 5,107 and 5,464 tokens to 2,050. The grouped condition saw different actual evidence from the expanded conditions, so 16/18 cannot support a grouping advantage.

Compare inside the full test

The rows below can come from different prompts and methods. Open the full test before treating two numbers as a direct comparison.

Recorded results

Home SOC: Four Models with Default Sampling

Four models answered the same saved log summaries. This group contains two tasks: structured reports with a two-minute deadline, and written reports with a five-minute deadline. The sampling settings use each model's defaults.

Each model received 12 structured tasks three times and 6 written tasks twice. Repeats test consistency on those tasks; they are not new incidents. Compare completion and explanations within the same task and settings. These runs do not measure each model's best possible performance.

Qwen3.5 4B

Structured report; default sampling

Partial result

Measured on Minisforum MS-S1 MAX · CPU

Finished reports: 36 of 36; 12 fixed log summaries, each asked 3 times. A finished report completed within 120 seconds and passed the report validator. (answers)
Passed full answer checklist: 3 of 30; 10 summaries contain alerts, each asked 3 times. A pass needs a finished answer, expected explanations, valid list lengths, no repeated selections/citations and the required review priority. (answers)
Expected explanations selected: 15 of 63; 21 expected explanation items across those 10 summaries, repeated 3 times. This counts selected items, not whole answers or new discoveries. (selections)

All 36 reports finished, though most missed expected explanations. The full answer checklist is stricter than completion; failing it does not mean every part of the answer was wrong.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · CPU · Native structured profile

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

Home SOC: Four Models with Default Sampling →

Qwen3.5 4B

Written report; default sampling

Partial result

Measured on Minisforum MS-S1 MAX · CPU

Finished reports: 8 of 12; 6 summaries with alerts, each asked twice. Only naturally finished answers count here. (answers)
Stopped at the output cap: 4 of 12; These answers returned text but reached the 700-token output limit before finishing. None of the written requests exceeded its 300-second deadline. (answers)
Finished answers with a major factual error: 2 of 8; One task produced a major factual error, repeated in both answers. Repeating it twice is not two different incidents. (answers)

The model claimed 14 groups where the supplied summary contained 16. That error repeated twice; unfinished answers were withheld.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · CPU · Native written profile

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

Home SOC: Four Models with Default Sampling →

Home SOC: Models Reading Simulation Logs

I converted the simulation logs into summaries, then asked each model to review them twice. Some simulations produced no alerts, so completion across all requests is shown separately from explanations on the summaries that contain alerts.

21 source cases produced 9 different summaries: 8 with alerts and 1 empty summary shared by 13 sources. Each model made 42 requests, but only 16 were the alert-bearing tasks (8 summaries, twice). Those repeats and duplicate empty inputs do not represent 42 different incidents.

Qwen3.5 4B

Simulation logs; default sampling

Partial result

Measured on Minisforum MS-S1 MAX · CPU

Finished reports: 42 of 42; 21 source cases, each asked twice. 13 sources produced the same empty summary, so this total includes duplicate inputs. (answers)
All expected explanations shown: 4 of 16; 8 different summaries contain alerts, each asked twice. An answer counts only when every expected explanation is visible in the rendered report. (answers)
Passed full answer checklist: 4 of 16; The same 16 alert-bearing attempts. The unedited answer must meet explanation, list-length, repetition and review-priority checks as well as finish. (answers)

Completion across all requests includes the empty summaries. Read the explanation and checklist counts for the 16 attempts with alerts. Identical repeated answers reused their source-linked agent review after exact identity checks.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · CPU · Native simulation-source profile

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

Home SOC: Models Reading Simulation Logs →

Home SOC: Four Models with Shared Sampling

Each model answered the same 12 tasks once with the sampling settings made explicit. Read completion first, then check whether the alert explanations and full answer checklist passed.

10 of the 12 tasks contain alerts. Completion uses all 12; explanation and checklist results use those 10. The 21 expected explanations count individual items across the same 10 tasks. This pass supports a choice for the scheduled report under these settings, not a general intelligence ranking.

Qwen3.5 4B

Structured report; shared sampling

Partial result

Measured on Minisforum MS-S1 MAX · CPU

Finished reports: 12 of 12; 12 fixed summaries asked once; 2 have no alerts. A report must finish within 120 seconds and pass the report validator. (answers)
All expected explanations shown: 7 of 10; 10 of those summaries contain alerts. Each pass means all expected explanations appear in the rendered report. (answers)
Passed full answer checklist: 4 of 10; The same 10 alert-bearing tasks. A pass also requires a finished answer, valid list lengths, no repeated selections/citations and the required review priority, before display cleanup. (answers)
Expected explanations selected: 18 of 21; 21 individual explanation items across the same 10 tasks. This is an item count, not 21 cases. (selections)

All 12 finished. Of the 10 tasks with alerts, 7 showed every expected explanation and 4 met the full answer checklist. The 18/21 count tracks individual explanation items within those same tasks.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · CPU · Explicit common profile

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

Home SOC: Four Models with Shared Sampling →

Home SOC: Investigation Failures and Input Fix

The original investigation answers failed. A revised task then exposed two prompts that were too long for the configured context. After fixing the instructions and ensuring the full input reached the model, I reran the same cases.

This is a correction history on 6 constructed cases, each tried in 3 conditions: evidence only, analyst assistance, and assistance with repetition grouping. That produces 18 measured answers, not 18 independent incidents. All 3 corrected conditions passed, so this test shows no accuracy advantage for assistance or grouping.

Qwen3.5 4B

Original V1 investigator

Failed run

Measured on Minisforum MS-S1 MAX · Recorded backend in request receipts

Answers passing evidence and decision checks: 0 of 18; 6 constructed measured cases × 3 conditions (answers)
Finished 9B reviews: 0 of 24; 18 measured plus 6 practice; all capped (answers)

Some answers copied real groups and then claimed there were no alerts; empty cases invented groups. Practice answers stayed outside the measured denominator.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · Recorded backend in request receipts · Original V1 investigator

Context window: 4,096 tokens for input and output together.

Installed artifact digest: d8b0f5e9760cd1682034f292d7ef72ec46f432149be0df7574bf2d6e92e38c04

Results and method Actual test host

Home SOC: Investigation Failures and Input Fix →

Qwen3.5 4B

Intermediate V5; invalid condition comparison

Failed run

Measured on Minisforum MS-S1 MAX · Recorded backend in request receipts

Recorded passes before the input fix: 16 of 18; Exposed regression set; two expanded inputs were truncated (answers)
Largest original expanded input: 5464 tokens; Truncated to 2050 under context 4096

Two inputs were cut from 5,107 and 5,464 tokens to 2,050. The grouped condition saw different actual evidence from the expanded conditions, so 16/18 cannot support a grouping advantage.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · Recorded backend in request receipts · Intermediate V5; invalid condition comparison

Context window: 4,096 tokens for input and output together.

Installed artifact digest: d8b0f5e9760cd1682034f292d7ef72ec46f432149be0df7574bf2d6e92e38c04

Results and method Actual test host

Home SOC: Investigation Failures and Input Fix →

Qwen3.5 4B

Corrected V6 condition A: evidence only

Partial result

Measured on Minisforum MS-S1 MAX · Recorded backend in request receipts

Answers passing evidence and decision checks: 6 of 6; The same 6 constructed cases, asked once in this condition with complete model input. These cases were already used during development. (answers)

6/6 passed in each of the three conditions. The model answered these known cases correctly after the input fix; assistance and grouping did not score higher than evidence alone. No humans took this test.

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · Recorded backend in request receipts · Corrected V6 condition A: evidence only

Context window: 8,192 tokens for input and output together.

Installed artifact digest: d8b0f5e9760cd1682034f292d7ef72ec46f432149be0df7574bf2d6e92e38c04

Results and method Actual test host

Home SOC: Investigation Failures and Input Fix →

Qwen3.5 4B

Corrected V6 condition B: analyst assistance

Partial result

Measured on Minisforum MS-S1 MAX · Recorded backend in request receipts

Answers passing evidence and decision checks: 6 of 6; The same 6 constructed cases, asked once in this condition with complete model input. These cases were already used during development. (answers)

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · Recorded backend in request receipts · Corrected V6 condition B: analyst assistance

Context window: 8,192 tokens for input and output together.

Installed artifact digest: d8b0f5e9760cd1682034f292d7ef72ec46f432149be0df7574bf2d6e92e38c04

Results and method Actual test host

Home SOC: Investigation Failures and Input Fix →

Qwen3.5 4B

Corrected V6 condition C: assistance plus grouping

Partial result

Measured on Minisforum MS-S1 MAX · Recorded backend in request receipts

Answers passing evidence and decision checks: 6 of 6; The same 6 constructed cases, asked once in this condition with complete model input. These cases were already used during development. (answers)

Setup and original evidence

Minisforum MS-S1 MAX · Ollama 0.35.1 · Recorded backend in request receipts · Corrected V6 condition C: assistance plus grouping

Context window: 8,192 tokens for input and output together.

Installed artifact digest: d8b0f5e9760cd1682034f292d7ef72ec46f432149be0df7574bf2d6e92e38c04

Results and method Actual test host

Home SOC: Investigation Failures and Input Fix →

Home SOC: One Report on the Radeon GPU

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.

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.

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

Home SOC: One Report on the Radeon GPU →

Full tests containing Qwen3.5 4B

2026-10-06

Home SOC: Four Models with Default Sampling

Open full test

2026-10-06

Home SOC: Models Reading Simulation Logs

Open full test

2026-10-06

Home SOC: Four Models with Shared Sampling

Open full test

2026-10-06

Home SOC: Investigation Failures and Input Fix

Open full test

2026-10-06

Home SOC: One Report on the Radeon GPU

Open full test