← Back to community benchmarks

gemma-4-31B-it-PARO

M1 Max (32c) · 64 GB · 4bit · 2026-05-24
Performance
16k
tokens
105.9
PP tok/s
11.7
TG tok/s
154660
TTFT (ms)
21.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 113.8 14.7 17.0 GB view
4k 110.8 13.9 19.5 GB view
8k 110.3 12.4 20.0 GB view
16k 105.9 11.7 21.7 GB current
32k 97.2 9.4 24.1 GB view
64k 85.2 6.6 30.1 GB view
128k 69.0 4.5 42.2 GB view
Batching Results
Batch Size TG tok/s Speedup
14.7 1.00×
19.4 1.32×
21.7 1.48×