← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-28
Performance
16k
tokens
3,350
PP tok/s
74.8
TG tok/s
4891
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,049 86.0 25.8 GB view
4k 3,067 83.6 26.4 GB view
8k 3,404 80.8 26.6 GB view
16k 3,350 74.8 27.1 GB current
32k 3,011 66.3 28.0 GB view
64k 2,260 50.8 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
86.0 1.00×
122.0 1.42×
171.8 2.00×