← Back to community benchmarks

LFM2-24B-A2B

M4 Pro (20c) · 64 GB · 4bit · 2026-03-09
Performance
4k
tokens
1,173
PP tok/s
101.1
TG tok/s
3493
TTFT (ms)
13.3
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,164 113.0 13.3 GB view
4k 1,173 101.1 13.3 GB current
8k 1,133 94.8 13.4 GB view
16k 1,050 79.4 13.5 GB view
Batching Results
Batch Size TG tok/s Speedup
113.0 1.00×
166.7 1.48×
207.7 1.84×
223.0 1.97×