← Back to community benchmarks

gemma-4-12B-it

M4 Pro (16c) · 24 GB · 4bit · 2026-06-04
Performance
4k
tokens
210.7
PP tok/s
19.4
TG tok/s
19437
TTFT (ms)
11.9
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.4.2.dev2
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 210.7 19.4 11.9 GB current
16k 204.1 18.5 12.7 GB view