← Back to community benchmarks

Laguna-S-2.1-oQ3e-fast

M1 Max (24c) · 64 GB · 3bit · 2026-07-25
Performance
16k
tokens
90.7
PP tok/s
21.3
TG tok/s
180716
TTFT (ms)
47.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 84.0 23.1 46.3 GB view
4k 98.5 24.5 46.5 GB view
8k 98.3 21.3 46.9 GB view
16k 90.7 21.3 47.4 GB current
32k 98.7 18.7 48.5 GB view
64k 56.7 15.9 49.4 GB view