Report · resources

Chat and code

Qwen3.8-27B · INT4 variant · NVIDIA NGC vLLM 0.29

Measured results / Chat and code / Run 3671f7ed4a19fa2721ae1f21

Measured time not recorded · Record date 2026-10-04

Not graded.

Writing speed, one personsingle_user_decode_tps · tok/s: 14.30 tok/sper person · single · sample count not recorded

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
Date	Shape	Each person · median	Machine total	First word · median	Result	Run
2026-10-05	1 people	not recorded	not recorded	0.81 s	Passed	Run c8b7c076 →
2026-10-05	1 people	not recorded	not recorded	8.60 s	Partial	Run f4c10f9c →
2026-10-05	unknown people	not recorded	not recorded	not recorded	Passed	Run 33a18763 →
2026-10-05	1 people	not recorded	not recorded	not recorded	Not graded	Run 7abd98af →
2026-10-04	1 people	not recorded	not recorded	not recorded	Not graded	Run 3671f7ed →

No answer-quality suite was graded for this run.

Recorded operator observation; exact model and engine identified. This historical seed did not retain request samples.

Recorded seed, not a fresh rerun; service targets and broad task quality unassessed.

Metric definitions, scope and statistics

All aggregate numeric result fields in this run
Metric	Value	Scope	Statistic	Sample count	Basis / source field	Run
single user decode tps	14.30 tok/s	per person	single	not recorded	single_user_decode_tps	Run 3671f7ed →

Skilak Keep evidence, run 3671f7ed4a19fa2721ae1f21, measured 2026-10-04.
https://skilak.ai/keep/resources/evidence/r/3671f7ed4a19fa2721ae1f21

Ready to scope it?

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