← Back to community benchmarks

gemma-4-26b-a4b-it-UD

M5 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
32k
tokens
3,276
PP tok/s
77.3
TG tok/s
10003
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,227 104.6 15.2 GB view
4k 3,348 99.5 15.7 GB view
8k 3,644 94.8 16.2 GB view
16k 3,603 88.7 16.5 GB view
32k 3,276 77.3 17.4 GB current
64k 2,516 59.7 19.4 GB view