← Leaderboard

Devstral Small 2 24B 6bit MLX

Tested Rank #17 of 33 · 4/8 GAUNTLET progress
Generalist — 78.5 / 100 G Agentic — 94.5 / 100 A Understanding — pending U Needle — pending N Thinking — 100 / 100 T Live — pending L Engineering — pending E Throughput — 12.4 / 100 T

Hollow markers & dashed spokes: axis not yet scored

G
78.5
A
94.5
U
N
T
100
L
E
T
12.4

Specification

Parameters
24B
Architecture
mistral3
Size on disk
19.43 GB
Quantization
6bit
Format
MLX
Reasoning (CoT)
No
Internal ID
M22
Mean speed
20.3 tok/s across suites
Stall census
0 stalls in 22 observed tests (0.0%)
Model card
huggingface.co

Suite results

Suite Score Avg / 20 Tests tok/s
General capability (13-task real-workload suite) 1a 204.1 / 260 15.7 13/13 17.7
Agentic tool-calling & protocol adherence 1b 151.2 / 160 18.9 8/8 22.9

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.