Runs on this setup
Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.
History and measured sweep
| Date | Shape | Each person · median | Machine total | First word · median | Result | Run |
|---|---|---|---|---|---|---|
2026-10-04 | unknown people | not recorded | not recorded | not recorded | Failed | |
2026-10-04 | unknown people | not recorded | not recorded | not recorded | Failed |
Answer checks
No answer-quality suite was graded for this run.
Method
Confirmed model trial with image verification and runtime readiness checks.
Limits
No successful inference result was produced; this failed attempt remains official evidence.
What did not work
- Image identity could not be verified.
What ran
Exact identity
- Original publisher model
- Qwen3.8-27B
- Publisher revision
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0- Variant · format · precision
- INT4 variant · safetensors · INT4
- Weights SHA-256
- not recorded
- Engine · version · feature
- vLLM ·
0.26.0· plain - Hardware
- NVIDIA GB10, 128 GB unified memory
- Harness / workload
not recorded- Workload suite · version
not recorded- Harness SHA-256
not recorded- Fixture SHA-256
not recorded
Workload shape
- Configured window (tokens)
- 8192
- Feature
- plain
Full reproduction pack available to customers and evaluators on request
All recorded numbers
Metric definitions, scope and statistics
| Metric | Value | Scope | Statistic | Sample count | Basis / source field |
|---|
Data and citation
Skilak Keep evidence, run 26af7cc2bed86f8fcf33bd65, measured 2026-10-04T10:43:24.538266+00:00. https://skilak.ai/keep/resources/evidence/r/26af7cc2bed86f8fcf33bd65
