← Back to community benchmarks

gemma-4-E4B-it

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-03
Performance
32k
tokens
2,095
PP tok/s
22.9
TG tok/s
15640
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 2,095 22.9 9.9 GB current
64k 1,912 30.3 10.5 GB view