← Back to community benchmarks

MiniMax-M2___5

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-12

Performance

4k

tokens

744.3

PP tok/s

39.5

TG tok/s

5504

TTFT (ms)

121.7

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.6

macOS macOS 15.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	646.9	46.2	120.7 GB	view
4k	744.3	39.5	121.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	46.2	1.00×
2×	71.1	1.54×
4×	102.5	2.22×