← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-28
Performance
4k
tokens
3,067
PP tok/s
83.6
TG tok/s
1336
TTFT (ms)
26.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.5
Context 4,096
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 current
8k 3,404 80.8 26.6 GB view
16k 3,350 74.8 27.1 GB view
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×