← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 6bit · 2026-05-04
Performance
32k
tokens
1,212
PP tok/s
66.4
TG tok/s
27036
TTFT (ms)
22.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,140 88.0 20.0 GB view
4k 1,354 85.1 20.7 GB view
8k 1,387 81.7 20.8 GB view
16k 1,338 75.5 21.3 GB view
32k 1,212 66.4 22.2 GB current
64k 1,011 8.6 70.0 GB view
Batching Results
Batch Size TG tok/s Speedup
88.0 1.00×
42.2 0.48×
88.8 1.01×
118.7 1.35×