← Back to community benchmarks

gemma-4-e4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-04-27
Performance
8k
tokens
992.9
PP tok/s
60.2
TG tok/s
8251
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 840.0 68.7 4.6 GB view
4k 981.5 65.0 4.7 GB view
8k 992.9 60.2 4.8 GB current
16k 970.9 48.4 4.9 GB view
32k 908.9 30.7 5.5 GB view
64k 796.8 17.4 6.6 GB view
Batching Results
Batch Size TG tok/s Speedup
68.7 1.00×
109.7 1.60×
278.0 4.05×