← Back to community benchmarks

gemma-4-e2b-it

M4 Pro (20c) · 48 GB · 4bit · 2026-05-21
Performance
8k
tokens
4,124
PP tok/s
104.5
TG tok/s
1987
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,646 114.5 4.0 GB view
4k 3,983 110.3 4.0 GB view
8k 4,124 104.5 4.1 GB current
16k 3,814 95.2 4.2 GB view
32k 3,257 81.3 4.5 GB view
64k 2,491 62.0 5.3 GB view
Batching Results
Batch Size TG tok/s Speedup
114.5 1.00×
212.2 1.85×
269.6 2.35×