← Back to community benchmarks

gemma-4-e4b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-04-26
Performance
8k
tokens
450.7
PP tok/s
32.9
TG tok/s
18175
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 387.0 42.8 4.6 GB view
4k 439.0 37.8 4.7 GB view
8k 450.7 32.9 4.8 GB current
16k 437.6 27.3 4.9 GB view
Batching Results
Batch Size TG tok/s Speedup
42.8 1.00×
51.9 1.21×
58.1 1.36×