← Back to community benchmarks

Huihui-gemma-4-E2B-it-abliterated-4bit-g32-mxfp4-mixed_4_8

M4 (10c) · 16 GB · 4bit · 2026-04-24
Performance
4k
tokens
2,183
PP tok/s
44.8
TG tok/s
1876
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,558 46.6 5.2 GB view
4k 2,183 44.8 5.3 GB current
Batching Results
Batch Size TG tok/s Speedup
46.6 1.00×
47.9 1.03×
50.9 1.09×