← Back to community benchmarks

LFM2-24B-A2B

M4 (10c) · 32 GB · 8bit · 2026-03-13

Performance

4k

tokens

593.5

PP tok/s

33.6

TG tok/s

6903

TTFT (ms)

24.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	576.5	35.9	24.1 GB	view
4k	593.5	33.6	24.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	35.9	1.00×
2×	45.6	1.27×
4×	52.9	1.47×