← Back to community benchmarks

gemma-4-e2b-it

M4 Pro (20c) · 48 GB · 4bit · 2026-05-21
Performance
16k
tokens
3,814
PP tok/s
95.2
TG tok/s
4296
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 16,384
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 view
16k 3,814 95.2 4.2 GB current
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×