← Back to community benchmarks

gemma-4-e4b-it

M3 Pro (18c) · 18 GB · 8bit · 2026-04-05
Performance
32k
tokens
855.1
PP tok/s
17.4
TG tok/s
38321
TTFT (ms)
9.0
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 18 GB
GPU Cores 18
Software
oMLX v0.3.3
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 779.5 24.3 8.0 GB view
8k 942.1 23.2 8.2 GB view
32k 855.1 17.4 9.0 GB current