← Leaderboard

Devstral Small 2 24B 4bit MLX

Retired Rank #23 of 33 · 2/8 GAUNTLET progress
Generalist — 74.5 / 100 G Agentic — pending A Understanding — pending U Needle — pending N Thinking — pending T Live — pending L Engineering — pending E Throughput — 21.2 / 100 T

Hollow markers & dashed spokes: axis not yet scored

G
74.5
A
U
N
T
n/d
L
E
T
21.2

Specification

Parameters
24B
Architecture
mistral3
Size on disk
14.12 GB
Quantization
4bit
Format
MLX
Reasoning (CoT)
No
Internal ID
M3
Mean speed
34.7 tok/s across suites
Stall census
0 stalls in 13 observed tests (0.0%)

Suite results

Suite Score Avg / 20 Tests tok/s
General capability (13-task real-workload suite) 1a 193.7 / 260 14.9 13/13 34.7

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.