FreshContextA context lab · Fife
Drawing
02 · Benchmarks
Sheet
2 of 3
Rev
A · 2026-10-01

Model · measured only← Models

sakura-iq3xxs-np2-128k-b11533

1 recorded run. This model has no written entry yet.

Scored runs
1
Run log entries
1
RecordIdentifier

sakura-iq3xxs-np2-128k-b11533

Every result below is as recorded. Without a written entry there is no stated reason for the test and no verdict.

Recorded runs1 scored · 95% intervals
SuiteScore95% interval PassedRuntime · profileRecorded
needle65.1%54.3–74.4Passed 54/83llama.cppextraction2026-10-11

Runs marked unenforced were measured through mlx_lm on a suite that requires constrained decoding. mlx_lm accepts the schema and ignores it, so those numbers do not measure what the suite is designed to measure. They are kept and labelled rather than deleted.

Every run log entry for this model (1)
FinishedSuiteRuntime · profileScoreCoverageGrader · dataset · config
needleneedle/1not recordedextraction65.1%Coverage 83/83g c38dec33aa1c86c2d 5c5199b9eee8a595c c420a150c3bfc6d4