← Back to community benchmarks

gemma-4-E4B-it-oQ8

M4 Max (40c) · 64 GB · 8bit · 2026-07-14
Performance
32k
tokens
1,661
PP tok/s
52.5
TG tok/s
19723
TTFT (ms)
9.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,847 61.2 8.4 GB view
32k 1,661 52.5 9.0 GB current
64k 1,488 42.4 9.6 GB view