/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.

10
result records
0
published result rows
5
test groups
1
devices represented

About Qwen3.5 4B

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Files and runtimes I tested

The results below cover Ollama 0.35.1. Open a configuration for the full test, including the model file or reporting profile, device, backend and settings.

2 rows record failed runs. The failure and original evidence stay attached to each result below.

Search and filter these results

Tested configurations

Recorded hosts, model variants, runtimes and backends for Qwen3.5 4B
DeviceFile or variantRuntimeBackendMode and settingsTest
Minisforum MS-S1 MAXStructured report; default samplingOllama 0.35.1CPUNative structured profile2 threads · 4,096 context tokensHome SOC: Four Models with Default Sampling
Minisforum MS-S1 MAXWritten report; default samplingOllama 0.35.1CPUNative written profile2 threads · 4,096 context tokensHome SOC: Four Models with Default Sampling
Minisforum MS-S1 MAXSimulation logs; default samplingOllama 0.35.1CPUNative simulation-source profile2 threads · 4,096 context tokensHome SOC: Models Reading Simulation Logs
Minisforum MS-S1 MAXStructured report; shared samplingOllama 0.35.1CPUExplicit common profile2 threads · 4,096 context tokensHome SOC: Four Models with Shared Sampling
Minisforum MS-S1 MAXOriginal V1 investigatorOllama 0.35.1Recorded backend in request receiptsOriginal V1 investigator4,096 context tokensHome SOC: Investigation Failures and Input Fix
Minisforum MS-S1 MAXIntermediate V5; invalid condition comparisonOllama 0.35.1Recorded backend in request receiptsIntermediate V5; invalid condition comparison4,096 context tokensHome SOC: Investigation Failures and Input Fix
Minisforum MS-S1 MAXCorrected V6 condition A: evidence onlyOllama 0.35.1Recorded backend in request receiptsCorrected V6 condition A: evidence only8,192 context tokensHome SOC: Investigation Failures and Input Fix
Minisforum MS-S1 MAXCorrected V6 condition B: analyst assistanceOllama 0.35.1Recorded backend in request receiptsCorrected V6 condition B: analyst assistance8,192 context tokensHome SOC: Investigation Failures and Input Fix
Minisforum MS-S1 MAXCorrected V6 condition C: assistance plus groupingOllama 0.35.1Recorded backend in request receiptsCorrected V6 condition C: assistance plus grouping8,192 context tokensHome SOC: Investigation Failures and Input Fix
Minisforum MS-S1 MAXFirst live GPU acceptanceOllama 0.35.1Vulkan / Radeon 8060SFirst live GPU acceptance2 threads · 4,096 context tokensHome SOC: One Report on the Radeon GPU

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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Expanded outcomes

    Native, simulation and common-profile phases, including written defects and withheld responses.

    MODEL_COMPARISON_EXPANDED_RESULTS.md
  • Offline verification

    Request hashes, frozen manifests and the boundaries of mechanical verification.

    MODEL_STUDY_VERIFICATION.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Expanded outcomes

    Native, simulation and common-profile phases, including written defects and withheld responses.

    MODEL_COMPARISON_EXPANDED_RESULTS.md
  • Offline verification

    Request hashes, frozen manifests and the boundaries of mechanical verification.

    MODEL_STUDY_VERIFICATION.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Simulation-source results

    Distinct inputs, duplicate empty briefs, repeated assessments and complete outcomes.

    MODEL_COMPARISON_EXPANDED_RESULTS.md
  • Simulation method

    Virtual lab, offline engine replay and physical inline test boundaries.

    SIMULATED_ACCEPTANCE_2026-10-05.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Common-profile results

    Exact settings, denominators, artifact identities and the configuration decision.

    MODEL_COMPARISON_EXPANDED_RESULTS.md
  • Refinement method

    Controls and reasons for keeping the result separate from model-size rankings.

    MODEL_REFINEMENT_RESULTS.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Original failures

    Preserved incorrect decisions, hallucinated groups and capped reviews.

    AUTOMATED_INVESTIGATION_RESULTS_2026-10-06.md
  • Corrected results

    V5 truncation, V6 full-input proof and unreliable reviewer controls.

    AUTOMATED_INVESTIGATION_CORRECTED_RESULTS_2026-10-06.md
  • Correction protocol

    Complete instructions, bounded decision slots and input-truncation guard.

    INVESTIGATION_CONTRACT_CORRECTION_2026-10-06.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Original failures

    Preserved incorrect decisions, hallucinated groups and capped reviews.

    AUTOMATED_INVESTIGATION_RESULTS_2026-10-06.md
  • Corrected results

    V5 truncation, V6 full-input proof and unreliable reviewer controls.

    AUTOMATED_INVESTIGATION_CORRECTED_RESULTS_2026-10-06.md
  • Correction protocol

    Complete instructions, bounded decision slots and input-truncation guard.

    INVESTIGATION_CONTRACT_CORRECTION_2026-10-06.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Original failures

    Preserved incorrect decisions, hallucinated groups and capped reviews.

    AUTOMATED_INVESTIGATION_RESULTS_2026-10-06.md
  • Corrected results

    V5 truncation, V6 full-input proof and unreliable reviewer controls.

    AUTOMATED_INVESTIGATION_CORRECTED_RESULTS_2026-10-06.md
  • Correction protocol

    Complete instructions, bounded decision slots and input-truncation guard.

    INVESTIGATION_CONTRACT_CORRECTION_2026-10-06.md
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)

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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Original failures

    Preserved incorrect decisions, hallucinated groups and capped reviews.

    AUTOMATED_INVESTIGATION_RESULTS_2026-10-06.md
  • Corrected results

    V5 truncation, V6 full-input proof and unreliable reviewer controls.

    AUTOMATED_INVESTIGATION_CORRECTED_RESULTS_2026-10-06.md
  • Correction protocol

    Complete instructions, bounded decision slots and input-truncation guard.

    INVESTIGATION_CONTRACT_CORRECTION_2026-10-06.md
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)

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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • Original failures

    Preserved incorrect decisions, hallucinated groups and capped reviews.

    AUTOMATED_INVESTIGATION_RESULTS_2026-10-06.md
  • Corrected results

    V5 truncation, V6 full-input proof and unreliable reviewer controls.

    AUTOMATED_INVESTIGATION_CORRECTED_RESULTS_2026-10-06.md
  • Correction protocol

    Complete instructions, bounded decision slots and input-truncation guard.

    INVESTIGATION_CONTRACT_CORRECTION_2026-10-06.md
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

Qwen3.5 4B is the model I selected for the scheduled Home SOC report under the shared settings I tested. The work runs on the Minisforum using evidence from the Vault. Completion, expected explanations and the full answer checklist are separate measurements on those reporting tasks.

Family
Qwen3.5
Recorded size
4B

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

Methods and supporting files

  • GPU deployment evidence

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

    SQLITE_GPU_AND_DEPLOYMENT_2026-10-06.md
Home SOC: One Report on the Radeon GPU →

Full tests containing Qwen3.5 4B

2026-10-06

Home SOC: Four Models with Default Sampling

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.

Open full test

2026-10-06

Home SOC: Models Reading Simulation Logs

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.

Open full test

2026-10-06

Home SOC: Four Models with Shared Sampling

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.

Open full test

2026-10-06

Home SOC: Investigation Failures and Input Fix

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.

Open full test

2026-10-06

Home SOC: One Report on the Radeon GPU

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.

Open full test

Methods and original files

Common-profile results

Exact settings, denominators, artifact identities and the configuration decision.

MODEL_COMPARISON_EXPANDED_RESULTS.md

Offline verification

Request hashes, frozen manifests and the boundaries of mechanical verification.

MODEL_STUDY_VERIFICATION.md

Simulation method

Virtual lab, offline engine replay and physical inline test boundaries.

SIMULATED_ACCEPTANCE_2026-10-05.md

Refinement method

Controls and reasons for keeping the result separate from model-size rankings.

MODEL_REFINEMENT_RESULTS.md

Original failures

Preserved incorrect decisions, hallucinated groups and capped reviews.

AUTOMATED_INVESTIGATION_RESULTS_2026-10-06.md

Corrected results

V5 truncation, V6 full-input proof and unreliable reviewer controls.

AUTOMATED_INVESTIGATION_CORRECTED_RESULTS_2026-10-06.md

Correction protocol

Complete instructions, bounded decision slots and input-truncation guard.

INVESTIGATION_CONTRACT_CORRECTION_2026-10-06.md

GPU deployment evidence

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

SQLITE_GPU_AND_DEPLOYMENT_2026-10-06.md

Model and file

A model name identifies the model. A variant such as Q4_K_M or IQ4_XS identifies the quantization used for a particular file. The artifact hash ties a result to the exact bytes I tested.

Runtime and backend

Ollama and llama.cpp run the model. CPU, Vulkan and RKLLM NPU paths describe where or how the computation ran. A successful CPU request and a failed GPU request can belong to the same model.

Generation and prompt processing

Generation measures output tokens per second. Prompt processing measures how quickly the input was processed. Open the test group for the workload, token counts and timing method behind each rate.

Context and report checks

The context window holds input and output together. In the Home SOC tests, completed reports, expected explanations and full answer checks have separate counts and denominators. Read the label beside each value.

Get an email when I publish new hardware reviews, benchmarks, and security research. Unsubscribe anytime.

Email goes to Buttondown. Privacy details.

© 2026 Trevor Unland. All rights reserved.

PrivacyTermsRSS Feed

$ echo "Built with React + TypeScript"