← Back to community benchmarks

gemma-4-e4b-it

M4 (10c) · 16 GB · 4bit · 2026-05-15
Performance
64k
tokens
459.8
PP tok/s
20.7
TG tok/s
142526
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 640.3 34.1 5.4 GB view
4k 647.1 33.3 5.5 GB view
8k 635.4 32.0 5.7 GB view
16k 610.1 29.9 5.9 GB view
32k 558.1 26.0 6.5 GB view
64k 459.8 20.7 7.0 GB current
Batching Results
Batch Size TG tok/s Speedup
34.1 1.00×
63.6 1.87×