← Back to community benchmarks

gemma-4-e4b-it

M1 Pro (14c) · 32 GB · 4bit · 2026-04-20
Performance
8k
tokens
399.5
PP tok/s
33.6
TG tok/s
20505
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.3.5
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 355.8 39.2 4.6 GB view
4k 392.9 36.8 4.7 GB view
8k 399.5 33.6 4.8 GB current
16k 393.5 28.5 4.9 GB view
32k 376.1 20.0 5.5 GB view
Batching Results
Batch Size TG tok/s Speedup
39.2 1.00×
46.3 1.18×
51.4 1.31×