← Back to community benchmarks

LFM2.5-8B-A1B

M5 Pro (20c) · 64 GB · 8bit · 2026-07-05
Performance
4k
tokens
3,905
PP tok/s
141.3
TG tok/s
1049
TTFT (ms)
9.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,956 143.9 8.9 GB view
4k 3,905 141.3 9.3 GB current
Batching Results
Batch Size TG tok/s Speedup
143.9 1.00×
170.6 1.19×
222.5 1.55×