Report · resources

Chat and code

Qwen3-8B-Base · Q4_K_M GGUF variant · llama.cpp b11182

Measured results / Chat and code / Run bd0a65e6b9c940f2bf691afe

Measured time not recorded · Record date 2026-10-09

Failed.

Peak memory, whole hostpeak_host_unavailable_gib · GiB
14.44 GiBmachine total · max · sample count not recorded

Answer checks

No answer-quality suite was graded for this run.

Method

Partial context speed attempt, stopped after observed whole-Mac swap growth.

Limits

Incomplete cohort; two-user filled-context speed not assessed in this attempt. Existing applications preserved. Shutdown during active work remains unqualified.

What did not work

  • Incomplete cohort; two-user filled-context speed not assessed in this attempt.

What ran

Exact identity

Original publisher model
Qwen3-8B-Base
Publisher revision
49e3418fbbbca6ecbdf9608b4d22e5a407081db4
Variant · format · precision
Q4_K_M GGUF variant · GGUF · Q4_K_M
Weights SHA-256
not recorded
Engine · version · feature
llama.cpp Metal · b11182 · plain
Hardware
Apple M6 Mac mini, 16 GiB 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
not recorded
Configured window (tokens)
9216
KV cache precision
q8_0
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
MetricValueScopeStatisticSample countBasis / source fieldRun
peak host unavailable gib
14.44 GiB
machine total
max
not recorded
peak_host_unavailable_gib

Data and citation

Skilak Keep evidence, run bd0a65e6b9c940f2bf691afe, measured 2026-10-09.
https://skilak.ai/keep/resources/evidence/r/bd0a65e6b9c940f2bf691afe

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.