← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 16 GB · 4bit · 2026-05-14
Performance
1k
tokens
642.8
PP tok/s
34.1
TG tok/s
1593
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 642.8 34.1 5.4 GB current
4k 647.0 33.1 5.5 GB view
8k 635.5 32.0 5.7 GB view
16k 609.8 29.8 5.9 GB view
32k 562.6 26.1 6.5 GB view
64k 470.5 20.6 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
34.1 1.00×
64.3 1.89×