← Back to community benchmarks

Mistral-Small-3.2-24B-Instruct-2506

M2 (10c) · 24 GB · 4bit · 2026-03-19

Performance

1k

tokens

34.5

PP tok/s

6.6

TG tok/s

29676

TTFT (ms)

13.0

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.19

macOS macOS 15.7.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	34.5	6.6	13.0 GB	current
4k	33.5	6.0	13.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	6.6	1.00×
2×	9.3	1.41×
4×	9.5	1.44×