← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-05-05
Performance
32k
tokens
231.7
PP tok/s
21.6
TG tok/s
141409
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 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 242.6 37.1 14.3 GB view
16k 247.6 30.0 15.4 GB view
32k 231.7 21.6 16.0 GB current
64k 203.4 15.0 17.7 GB view
128k 159.6 9.4 21.2 GB view