← Back to community benchmarks

Huihui-Qwen3.5-9B-abliterated

M4 (8c) · 16 GB · 4bit · 2026-04-24
Performance
4k
tokens
168.6
PP tok/s
21.0
TG tok/s
24293
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 165.1 21.7 5.7 GB view
4k 168.6 21.0 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
21.7 1.00×
38.8 1.79×
40.2 1.85×