← Back to community benchmarks

gemma-4-E4B-it

M1 (7c) · 16 GB · 6bit · 2026-05-07
Performance
16k
tokens
183.8
PP tok/s
8.1
TG tok/s
89136
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 191.4 11.0 7.9 GB view
4k 193.4 10.7 8.0 GB view
8k 187.0 9.5 8.2 GB view
16k 183.8 8.1 8.4 GB current
32k 146.6 6.5 8.7 GB view
64k 128.9 4.1 9.5 GB view