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 |
|---|---|---|---|---|---|---|
2026-10-05 | 1 people | not recorded | 56.92 tok/s | not recorded | Partial | |
2026-10-05 | unknown people | not recorded | not recorded | not recorded | Failed | |
2026-10-05 | unknown people | not recorded | not recorded | not recorded | Failed | |
2026-10-05 | unknown people | not recorded | not recorded | not recorded | Partial |
Answer checks
No answer-quality suite was graded for this run.
Method
Earlier managed-package attempt; exact measurement time unrecorded. No final-drive figures are attributed to this attempt.
Limits
Failure retained. Earlier images and request settings differ from the final drive; no package promotion.
What did not work
- CUDA allocation failed during context initialization before weight loading. No other engine was running. A later retry after per-file cache advice started successfully; this does not establish the sole cause.
What ran
Exact identity
- Original publisher model
- Qwen3.8-27B
- Publisher revision
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0- Variant · format · precision
- NVFP4 variant · safetensors · NVFP4
- Weights SHA-256
- not recorded
- Engine · version · feature
- SGLang ·
version not recorded· speculative decoding - 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
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 b749797cadad45718f30c3c9, measured 2026-10-05. https://skilak.ai/keep/resources/evidence/r/b749797cadad45718f30c3c9
