SkilakKeep
Request a pilot

Report · resources

Chat and code

Qwen3.8-27B · INT4 variant · NVIDIA NGC vLLM 0.29 · with multi-token prediction

Measured results / Chat and code / Run 6d39ad79aafbfdac807c2434

Measured time not recorded · Record date 2026-10-05

Not graded.

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

Answer checks

No answer-quality suite was graded for this run.

Method

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

Limits

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

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
NVIDIA NGC vLLM · 0.29.0+5013de39.dev · with multi-token prediction
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

People in this run
1
Configured window (tokens)
8192
Feature
with multi-token prediction

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 fieldRun
single user decode tps
23.30 tok/s
per person
single
not recorded
single_user_decode_tps

Data and citation

Download this run · OLIR JSONAll numbers · CSVOLIR schema
Skilak Keep evidence, run 6d39ad79aafbfdac807c2434, measured 2026-10-05.
https://skilak.ai/keep/resources/evidence/r/6d39ad79aafbfdac807c2434

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.

Request a pilot