← Back to community benchmarks

gemma-4-31b

M2 Ultra (76c) · 192 GB · 4bit · 2026-05-14
Performance
4k
tokens
179.9
PP tok/s
24.8
TG tok/s
22777
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 169.9 26.1 17.8 GB view
4k 179.9 24.8 20.2 GB current
8k 179.5 23.4 20.7 GB view
16k 175.5 20.9 22.1 GB view
32k 167.1 16.8 24.8 GB view
64k 145.2 12.4 31.4 GB view
Batching Results
Batch Size TG tok/s Speedup
26.1 1.00×
33.7 1.29×
68.4 2.62×
137.1 5.25×