Report · resources

Structured tasks

Qwen3.8-27B · INT4 variant · vLLM 0.26

Measured results / Structured tasks / Run 290d4246df1c6aa7fa2b7f63

Measured 2026-10-04 19:07 UTC · Record date 2026-10-04

Failed.

Runs on this setup

Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.

History and measured sweep
History of this setup, newest first
DateShapeEach person · medianMachine totalFirst word · medianResultRun
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

  • Runtime did not become healthy.

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
All aggregate numeric result fields in this run
MetricValueScopeStatisticSample countBasis / source field

Data and citation

Skilak Keep evidence, run 290d4246df1c6aa7fa2b7f63, measured 2026-10-04T19:07:35.739229+00:00.
https://skilak.ai/keep/resources/evidence/r/290d4246df1c6aa7fa2b7f63

Ready to scope it?

Start with one workload.

Tell us who uses it, what it can read, and what must stay inside. We will map the build.