← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-16
Performance
64k
tokens
2,051
PP tok/s
46.1
TG tok/s
31952
TTFT (ms)
29.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,190 87.6 25.8 GB view
4k 3,186 85.1 26.4 GB view
8k 3,470 81.5 26.7 GB view
16k 3,134 74.7 27.1 GB view
32k 2,616 64.1 27.5 GB view
64k 2,051 46.1 29.2 GB current
Batching Results
Batch Size TG tok/s Speedup
87.6 1.00×
107.5 1.23×
151.4 1.73×
192.8 2.20×