← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-27
Performance
8k
tokens
1,347
PP tok/s
71.9
TG tok/s
6084
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.11
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,155 68.8 25.8 GB view
4k 1,290 73.2 26.4 GB view
8k 1,347 71.9 26.6 GB current
16k 1,303 66.2 27.1 GB view
32k 1,174 56.4 28.0 GB view
64k 954.5 46.6 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
68.8 1.00×
110.6 1.61×
148.8 2.16×
194.9 2.83×