← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-31
Performance
16k
tokens
1,333
PP tok/s
66.4
TG tok/s
12291
TTFT (ms)
26.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,158 74.6 25.8 GB view
16k 1,333 66.4 26.9 GB current
64k 1,003 47.7 29.7 GB view
195k 565.6 26.6 37.9 GB view
Batching Results
Batch Size TG tok/s Speedup
74.6 1.00×
115.0 1.54×
153.8 2.06×