← Back to community benchmarks

gemma-4-e4b-it-oQ4

M1 Pro (16c) · 16 GB · 4bit · 2026-04-18
Performance
16k
tokens
694.8
PP tok/s
30.6
TG tok/s
23582
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 694.8 30.6 5.0 GB current
32k 642.6 17.4 5.6 GB view