← Back to community benchmarks

gemma-4-E4B-it-heretic-oQ4

M4 Max (40c) · 48 GB · 4bit · 2026-04-15
Performance
4k
tokens
2,188
PP tok/s
97.3
TG tok/s
1872
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,672 104.0 4.8 GB view
4k 2,188 97.3 4.8 GB current