← Back to community benchmarks

gemma-4-31b-it

M1 Ultra (48c) · 128 GB · 4bit · 2026-04-05
Performance
1k
tokens
112.0
PP tok/s
14.9
TG tok/s
9146
TTFT (ms)
18.0
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 128 GB
GPU Cores 48
Software
oMLX v0.3.2
macOS macOS 15.7.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 112.0 14.9 18.0 GB current
4k 111.1 10.8 19.6 GB view
8k 110.1 10.9 19.8 GB view
Batching Results
Batch Size TG tok/s Speedup
14.9 1.00×
17.1 1.15×
19.6 1.32×