← Back to community benchmarks

gemma-4-12B-it

M5 Max (40c) · 128 GB · bf16 · 2026-06-03
Performance
16k
tokens
1,754
PP tok/s
14.4
TG tok/s
9341
TTFT (ms)
25.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,754 14.4 25.2 GB current
64k 1,166 8.0 28.4 GB view
128k 770.9 5.6 32.8 GB view