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

Model · measured only← Models

gemma4-e2b-mlx-4bit

2 recorded runs. This model has no written entry yet.

Scored runs
2
Run log entries
2
RecordIdentifier

gemma4-e2b-mlx-4bit

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

Recorded runs2 scored · 95% intervals
SuiteScore95% interval PassedRuntime · profileRecorded
tagger85.8%80.9–89.7Passed 206/240mlxextraction2026-09-07
tagger_nullable73.8%67.8–78.9Passed 177/240mlxextraction2026-09-07

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 (2)
FinishedSuiteRuntime · profileScoreCoverageGrader · dataset · config
tagger_nullabletagger-nullable/1mlxextraction73.8%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec d40c89a4c0ded16e
taggertagger/2mlxextraction85.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 1623b2cdd0ccbfaf