← Back to community benchmarks

LFM2-1.2BoQ4

M4 (10c) · 16 GB · 4bit · 2026-07-17
Performance
195k
tokens
471.7
PP tok/s
33.2
TG tok/s
423962
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,570 131.0 1.3 GB view
4k 1,502 116.7 1.4 GB view
8k 1,424 100.4 1.5 GB view
16k 1,314 76.4 1.6 GB view
32k 1,134 85.3 1.7 GB view
64k 890.8 61.4 2.1 GB view
128k 622.6 39.2 3.1 GB view
195k 471.7 33.2 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
131.0 1.00×
260.1 1.99×
522.1 3.99×
1046.2 7.99×