← Back to community benchmarks

gemma-4-12B-it

M4 Max (40c) · 64 GB · 8bit · 2026-06-04
Performance
16k
tokens
487.3
PP tok/s
30.1
TG tok/s
33623
TTFT (ms)
13.9
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 487.3 30.1 13.9 GB current
32k 452.1 28.5 15.1 GB view
64k 379.4 23.7 17.1 GB view