← Back to community benchmarks

gemma-4-e4b-it

M1 Pro (14c) · 16 GB · 8bit · 2026-04-17
Performance
8k
tokens
397.5
PP tok/s
24.6
TG tok/s
20607
TTFT (ms)
8.2
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 16 GB
GPU Cores 14
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 352.6 28.1 8.0 GB view
4k 396.7 26.6 8.1 GB view
8k 397.5 24.6 8.2 GB current
16k 393.3 20.7 8.4 GB view
32k 375.0 15.5 9.0 GB view
Batching Results
Batch Size TG tok/s Speedup
28.1 1.00×
47.0 1.67×
54.8 1.95×