← Back to community benchmarks

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

M2 (10c) · 24 GB · 4bit · 2026-03-19
Performance
4k
tokens
33.5
PP tok/s
6.0
TG tok/s
122147
TTFT (ms)
13.8
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.19
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 34.5 6.6 13.0 GB view
4k 33.5 6.0 13.8 GB current
Batching Results
Batch Size TG tok/s Speedup
6.6 1.00×
9.3 1.41×
9.5 1.44×