← Back to community benchmarks

gemma-4-12B-it

M1 Max (24c) · 32 GB · 8bit · 2026-06-04
Performance
32k
tokens
128.4
PP tok/s
16.9
TG tok/s
255227
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.4.2.dev1
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 147.0 20.4 12.8 GB view
4k 143.2 19.2 13.9 GB view
8k 137.1 18.1 14.0 GB view
16k 133.2 17.8 14.3 GB view
32k 128.4 16.9 15.1 GB current
64k 116.7 15.4 17.0 GB view
Batching Results
Batch Size TG tok/s Speedup
20.4 1.00×
23.5 1.15×
26.8 1.31×