← Back to community benchmarks

Gemma-4-31B4.9bit-vision

M4 Max (32c) · 36 GB · 4bit · 2026-05-04
Performance
1k
tokens
161.8
PP tok/s
16.9
TG tok/s
6329
TTFT (ms)
19.0
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024