← Back to community benchmarks

gemma-3-12b-it-qat

M2 Max (30c) · 64 GB · 4bit · 2026-03-11
Performance
32k
tokens
190.4
PP tok/s
3.3
TG tok/s
172132
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 202.0 35.0 8.5 GB view
4k 200.4 33.1 9.2 GB view
8k 198.9 27.0 9.5 GB view
16k 196.5 20.7 10.2 GB view
32k 190.4 3.3 11.7 GB current
Batching Results
Batch Size TG tok/s Speedup
35.0 1.00×
70.1 2.00×
140.5 4.01×