← Leaderboard

Gemma 3 4B QAT 4bit MLX

Tested Rank #28 of 33 · 2/8 GAUNTLET progress
Generalist — 61.5 / 100 G Agentic — pending A Understanding — pending U Needle — pending N Thinking — pending T Live — pending L Engineering — pending E Throughput — 100 / 100 T

Hollow markers & dashed spokes: axis not yet scored

G
61.5
A
U
N
T
n/d
L
E
T
100

Specification

Parameters
4B
Architecture
gemma3
Size on disk
2.8 GB
Quantization
QAT 4bit
Format
MLX
Reasoning (CoT)
No
Internal ID
M16
Mean speed
163.3 tok/s across suites
Stall census
0 stalls in 13 observed tests (0.0%)
Model card
lmstudio.ai

Suite results

Suite Score Avg / 20 Tests tok/s
General capability (13-task real-workload suite) 1a 159.9 / 260 12.3 13/13 163.3

Each test is LLM-judged 0–20 against a fixed rubric; suite max = tests × 20. Where fewer tests ran than the suite total, unrun tests count as zero toward the axis score. See methodology.