← Back to community benchmarks

gemma-4-e4b-it

M1 Max (32c) · 32 GB · 4bit · 2026-05-12
Performance
8k
tokens
907.7
PP tok/s
57.7
TG tok/s
9025
TTFT (ms)
6.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 922.1 65.9 5.7 GB view
4k 917.3 62.3 5.8 GB view
8k 907.7 57.7 6.0 GB current
16k 887.1 50.9 6.4 GB view
32k 845.5 40.4 7.1 GB view
64k 769.3 26.6 8.8 GB view