← Back to community benchmarks

LFM2-8B-A1B

M4 (10c) · 16 GB · 4bit · 2026-03-09
Performance
4k
tokens
825.6
PP tok/s
79.6
TG tok/s
4962
TTFT (ms)
6.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
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 839.3 86.9 6.0 GB view
4k 825.6 79.6 6.2 GB current
Batching Results
Batch Size TG tok/s Speedup
86.9 1.00×
118.2 1.36×
128.1 1.47×