← Back to community benchmarks

gemma-4-e4b-it

M4 (8c) · 16 GB · 4bit · 2026-05-18
Performance
8k
tokens
481.7
PP tok/s
30.7
TG tok/s
17008
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 489.1 33.6 5.4 GB view
4k 489.7 31.7 5.5 GB view
8k 481.7 30.7 5.7 GB current
16k 461.3 28.6 5.9 GB view
32k 422.8 25.0 6.5 GB view
64k 348.1 20.0 7.6 GB view
Batching Results
Batch Size TG tok/s Speedup
33.6 1.00×
55.8 1.66×
60.3 1.79×