← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-20
Performance
16k
tokens
3,662
PP tok/s
89.6
TG tok/s
4475
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,232 105.8 15.2 GB view
4k 3,436 101.5 15.5 GB view
8k 3,734 97.4 15.7 GB view
16k 3,662 89.6 16.1 GB current
32k 3,264 77.9 16.9 GB view
64k 2,600 62.0 18.6 GB view
128k 1,787 43.6 22.1 GB view
Batching Results
Batch Size TG tok/s Speedup
105.8 1.00×
157.8 1.49×
218.2 2.06×