← Back to community benchmarks

gemma-4-31B-it-mxfp4

M3 Max (30c) · 96 GB · 4bit · 2026-04-12
Performance
1k
tokens
130.4
PP tok/s
14.2
TG tok/s
7855
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 130.4 14.2 19.9 GB current
4k 120.5 14.2 22.4 GB view