← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (16c) · 48 GB · 4bit · 2026-05-08
Performance
32k
tokens
1,594
PP tok/s
52.2
TG tok/s
20556
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M5 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 1,276 73.9 14.3 GB view
4k 1,721 70.9 15.0 GB view
8k 1,806 67.1 15.1 GB view
16k 1,767 61.3 15.6 GB view
32k 1,594 52.2 16.5 GB current
64k 1,257 40.4 18.5 GB view