← Back to community benchmarks

gemma-4-E4B-it

M4 Max (40c) · 128 GB · 4bit · 2026-06-01
Performance
32k
tokens
2,145
PP tok/s
52.5
TG tok/s
15280
TTFT (ms)
7.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8.dev3
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 2,145 52.5 7.9 GB current
64k 1,750 38.3 8.6 GB view