← Back to community benchmarks

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

M3 Ultra (60c) · 256 GB · 6bit · 2026-03-19
Performance
1k
tokens
361.9
PP tok/s
34.0
TG tok/s
2832
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 361.9 34.0 19.4 GB current
4k 364.2 31.3 20.1 GB view
8k 355.3 28.4 20.7 GB view
16k 336.7 23.5 21.9 GB view
Batching Results
Batch Size TG tok/s Speedup
34.0 1.00×
41.0 1.21×
46.8 1.38×