Report · resources

Structured tasks

Qwen3.8-27B · Mirai S trellis with Q8_0 MTP GGUF variant · Mirai S CUDA dev · with multi-token prediction

Measured results / Structured tasks / Run 424b33c36c884565a9c6fc0a

Measured 2026-10-09 14:13 UTC · Record date 2026-10-09

Not graded. 8/8 request checks

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
2026-10-09	1 people	not recorded	not recorded	not recorded	Passed	Run 729aab16 →
2026-10-09	1 people	not recorded	not recorded	not recorded	Not graded	Run 424b33c3 →

Answer checks

8/8 request checks

Method

Frozen probes: four benign and four clearly harmful requests, same system text/template, temperature zero and seed 17. Responses retained privately; explicit behaviour review pending.

Limits

Finite non-refusal/refusal labels are not general safety certification. Truncated benign answers show non-refusal only.

What ran

Exact identity

Original publisher model: Qwen3.8-27B
Publisher revision: 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
Variant · format · precision: Mirai S trellis with Q8_0 MTP GGUF variant · GGUF · Mirai S trellis with Q8_0 MTP
Weights SHA-256: af3e2d508cb12ebf68688a0756da6bcb4cdfceca3883f5751666d5e4fb34a334
Engine · version · feature: Mirai S CUDA · 0.2.0-dev-vector-disabled · with multi-token prediction
Hardware: NVIDIA GeForce RTX 3060, 12 GB VRAM
Harness / workload: not recorded
Workload suite · version: not recorded
Harness SHA-256: not recorded
Fixture SHA-256: 93b444104682a88ecb100c566125d325362711858498e853994240a89049dd8d

Workload shape

People in this run: 1
Configured window (tokens): 262144
Configured window (tokens): 262144
KV cache precision: q8_0
Output token ceiling: 512
Feature: with multi-token prediction
Thinking: off

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
Metric	Value	Scope	Statistic	Sample count	Basis / source field	Run
requests ok	8.00 count	machine total	single	not recorded	requests_ok	Run 424b33c3 →
requests total	8.00 count	machine total	single	not recorded	requests_total	Run 424b33c3 →

Data and citation

Download this run · OLIR JSON All numbers · CSV OLIR schema

Skilak Keep evidence, run 424b33c36c884565a9c6fc0a, measured 2026-10-09T14:13:52.607969+00:00.
https://skilak.ai/keep/resources/evidence/r/424b33c36c884565a9c6fc0a

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