← Back to community benchmarks

gemma-4-E4B-it

M4 (10c) · 32 GB · 4bit · 2026-04-17
Performance
16k
tokens
583.7
PP tok/s
17.0
TG tok/s
28067
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 15.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 500.5 20.2 6.0 GB view
4k 587.9 19.7 6.0 GB view
8k 600.9 19.2 6.1 GB view
16k 583.7 17.0 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
20.2 1.00×
39.3 1.95×
64.8 3.21×