← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-20
Performance
32k
tokens
3,295
PP tok/s
78.1
TG tok/s
9944
TTFT (ms)
16.9
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 2,254 105.3 15.2 GB view
4k 3,413 100.7 15.5 GB view
8k 3,677 97.3 15.7 GB view
16k 3,616 90.1 16.1 GB view
32k 3,295 78.1 16.9 GB current
64k 2,604 61.8 18.6 GB view
128k 1,785 43.7 22.1 GB view
Batching Results
Batch Size TG tok/s Speedup
105.3 1.00×
160.3 1.52×
219.9 2.09×