← Back to community benchmarks

gemma-4-E4B-it

M4 Pro (20c) · 24 GB · 4bit · 2026-05-14
Performance
16k
tokens
1,192
PP tok/s
41.7
TG tok/s
13745
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 24 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 15.7.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,232 47.0 7.0 GB view
4k 1,225 45.8 7.1 GB view
8k 1,237 44.3 7.3 GB view
16k 1,192 41.7 7.5 GB current
32k 1,096 36.9 8.2 GB view
64k 922.1 29.9 9.1 GB view
Batching Results
Batch Size TG tok/s Speedup
47.0 1.00×
90.2 1.92×
123.1 2.62×