← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (16c) · 48 GB · 4bit · 2026-05-05
Performance
32k
tokens
516.5
PP tok/s
40.3
TG tok/s
63439
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
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 577.8 66.0 14.3 GB view
4k 610.8 62.5 14.9 GB view
8k 604.8 59.6 15.3 GB view
16k 576.6 52.2 15.6 GB view
32k 516.5 40.3 16.5 GB current
64k 428.9 25.7 17.7 GB view
128k 311.1 12.5 21.2 GB view