← Back to community benchmarks

gemma-4-e4b-it-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-04-18
Performance
8k
tokens
626.8
PP tok/s
23.1
TG tok/s
13070
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
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 566.3 28.5 6.4 GB view
4k 627.3 27.6 6.5 GB view
8k 626.8 23.1 6.5 GB current