← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 24 GB · 8bit · 2026-04-05
Performance
32k
tokens
550.1
PP tok/s
12.2
TG tok/s
59565
TTFT (ms)
9.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.2
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 598.1 13.6 9.2 GB view
32k 550.1 12.2 9.6 GB current
64k 465.7 9.6 10.4 GB view