← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-05-26
Performance
8k
tokens
254.7
PP tok/s
33.3
TG tok/s
32157
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 241.8 37.4 14.3 GB view
4k 254.4 35.4 14.9 GB view
8k 254.7 33.3 15.1 GB current
16k 247.5 25.6 15.6 GB view
32k 231.4 16.4 16.0 GB view
64k 203.1 11.1 17.7 GB view