← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-25
Performance
16k
tokens
2,824
PP tok/s
75.3
TG tok/s
5802
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.10
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,091 88.0 25.8 GB view
4k 3,149 85.0 26.4 GB view
8k 3,227 81.5 26.6 GB view
16k 2,824 75.3 27.1 GB current
32k 2,466 65.6 28.0 GB view
64k 1,937 47.4 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
88.0 1.00×
118.0 1.34×
146.3 1.66×