← Back to community benchmarks

gemma-4-31B-it-oQ8

M1 Max (24c) · 64 GB · 8bit · 2026-05-18
Performance
16k
tokens
50.5
PP tok/s
7.3
TG tok/s
324129
TTFT (ms)
36.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 51.7 8.3 31.8 GB view
4k 51.5 8.1 34.5 GB view
8k 51.9 7.9 35.0 GB view
16k 50.5 7.3 36.1 GB current
32k 45.8 4.7 39.2 GB view
64k 41.5 4.7 45.1 GB view