← Back to community benchmarks

gemma-4-12B-it

M4 Max (40c) · 64 GB · 4bit · 2026-06-05
Performance
32k
tokens
428.3
PP tok/s
27.2
TG tok/s
76506
TTFT (ms)
13.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.2.dev2
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 457.7 27.9 12.6 GB view
32k 428.3 27.2 13.8 GB current
64k 372.4 23.4 15.7 GB view