← Back to community benchmarks

local--Laguna-S-2.1oQ4e-fast-gs128

M5 Max (40c) · 128 GB · 4bit · 2026-07-23
Performance
32k
tokens
836.3
PP tok/s
55.2
TG tok/s
39184
TTFT (ms)
61.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,103 68.0 60.0 GB view
8k 978.6 65.9 60.1 GB view
16k 893.7 62.4 60.5 GB view
32k 836.3 55.2 61.3 GB current
64k 749.6 45.5 62.9 GB view