← Back to community benchmarks

gemma-4-E4B-it-ultra-uncensored-heretic4bit-mixed_4_6

M4 Max (40c) · 128 GB · 4bit · 2026-05-05
Performance
32k
tokens
1,711
PP tok/s
58.2
TG tok/s
19153
TTFT (ms)
7.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,067 76.2 6.5 GB view
4k 2,152 85.5 6.7 GB view
8k 1,953 80.8 6.8 GB view
16k 1,821 68.8 7.0 GB view
32k 1,711 58.2 7.7 GB current
64k 1,612 46.2 8.6 GB view
128k 1,085 30.2 9.8 GB view
Batching Results
Batch Size TG tok/s Speedup
76.2 1.00×
128.8 1.69×
161.0 2.11×
159.7 2.10×