← Back to community benchmarks

Huihui-Qwen3.5-9B-abliterated

M3 Pro (18c) · 36 GB · 4bit · 2026-03-11
Performance
1k
tokens
326.3
PP tok/s
28.2
TG tok/s
3139
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 36 GB
GPU Cores 18
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 326.3 28.2 5.8 GB current
4k 343.0 26.6 6.5 GB view
Batching Results
Batch Size TG tok/s Speedup
28.2 1.00×
51.7 1.83×
80.6 2.86×