← Back to community benchmarks

Ministral-3-14B-Instruct-2512

M3 Pro (14c) · 18 GB · 4bit · 2026-05-10

Performance

4k

tokens

127.6

PP tok/s

14.1

TG tok/s

32108

TTFT (ms)

8.5

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.3.8

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	142.6	16.5	8.0 GB	view
4k	127.6	14.1	8.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	16.5	1.00×
2×	24.3	1.47×
4×	28.7	1.74×