← Back to community benchmarks

LFM2-24B-A2B

M3 Max (30c) · 36 GB · 4bit · 2026-03-12

Performance

4k

tokens

1,436

PP tok/s

106.1

TG tok/s

2852

TTFT (ms)

13.3

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.2.9

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,235	118.1	13.3 GB	view
4k	1,436	106.1	13.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	118.1	1.00×
2×	166.4	1.41×
4×	204.5	1.73×
8×	257.3	2.18×