← Back to community benchmarks

gemma-4-e2b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-05-04
Performance
16k
tokens
3,248
PP tok/s
94.5
TG tok/s
5044
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,719 116.6 4.0 GB view
4k 3,672 112.1 4.0 GB view
8k 3,528 105.3 4.1 GB view
16k 3,248 94.5 4.2 GB current
32k 2,788 79.3 4.5 GB view
64k 2,166 60.2 5.2 GB view
128k 1,464 40.4 6.7 GB view
Batching Results
Batch Size TG tok/s Speedup
116.6 1.00×
190.3 1.63×
228.3 1.96×