← Back to community benchmarks

gemma-4-e4b-it-OptiQ

M4 Max (40c) · 128 GB · 4bit · 2026-05-29
Performance
4k
tokens
1,999
PP tok/s
84.8
TG tok/s
2049
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,401 87.7 6.8 GB view
4k 1,999 84.8 6.9 GB current
8k 2,188 81.2 7.0 GB view
16k 2,176 72.8 7.2 GB view
32k 1,960 61.2 7.9 GB view
64k 1,590 44.9 8.8 GB view
128k 1,278 30.0 11.1 GB view
Batching Results
Batch Size TG tok/s Speedup
87.7 1.00×
128.6 1.47×
192.6 2.20×
227.4 2.59×