← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 24 GB · 4bit · 2026-05-17
Performance
16k
tokens
607.8
PP tok/s
29.7
TG tok/s
26955
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 643.3 34.1 5.4 GB view
4k 645.6 32.8 5.5 GB view
8k 634.7 32.1 5.7 GB view
16k 607.8 29.7 5.9 GB current
32k 532.0 25.5 6.5 GB view
64k 450.0 20.7 7.6 GB view
Batching Results
Batch Size TG tok/s Speedup
34.1 1.00×
62.4 1.83×
77.6 2.28×
82.7 2.43×