← Back to community benchmarks

Ministral-3-14B-Reasoning-2512

M1 Max (32c) · 64 GB · bf16 · 2026-04-06
Performance
8k
tokens
252.3
PP tok/s
10.8
TG tok/s
32479
TTFT (ms)
27.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.4
macOS macOS 15.7.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 261.1 12.3 25.7 GB view
4k 265.3 11.6 26.3 GB view
8k 252.3 10.8 27.0 GB current
16k 227.7 9.3 28.2 GB view
32k 186.9 7.4 30.7 GB view
64k 138.6 5.2 35.8 GB view
Batching Results
Batch Size TG tok/s Speedup
12.3 1.00×
8.8 0.72×
17.4 1.41×