← Back to community benchmarks

Devstral-Small-2-24B-Instruct-2512

M5 Max (40c) · 128 GB · 4bit · 2026-05-18

Performance

1k

tokens

992.9

PP tok/s

39.5

TG tok/s

1031

TTFT (ms)

13.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	992.9	39.5	13.2 GB	current
4k	1,060	37.4	14.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	39.5	1.00×
2×	72.5	1.84×
4×	86.0	2.18×