← Back to community benchmarks

gemma-4-e4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-18
Performance
64k
tokens
758.7
PP tok/s
28.7
TG tok/s
86374
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,432 80.5 5.6 GB view
4k 3,478 77.8 5.7 GB view
8k 4,092 74.0 5.8 GB view
16k 3,745 66.9 6.0 GB view
32k 3,551 56.5 6.7 GB view
64k 758.7 28.7 7.1 GB current
Batching Results
Batch Size TG tok/s Speedup
80.5 1.00×
146.1 1.81×
203.2 2.52×