← Back to community benchmarks

local--Agents-A1

M5 Max (40c) · 128 GB · 4bit · 2026-07-01
Performance
64k
tokens
1,101
PP tok/s
79.5
TG tok/s
59527
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.5.dev1
macOS macOS 26.5.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,708 119.8 19.2 GB view
4k 4,379 122.1 20.0 GB view
8k 4,134 116.7 20.4 GB view
16k 2,429 110.2 20.3 GB view
32k 1,806 104.2 20.6 GB view
64k 1,101 79.5 21.2 GB current
128k 650.2 58.8 22.4 GB view