← Back to community benchmarks

Qwen3.5-9B-OptiQ

M3 Max (40c) · 64 GB · 4bit · 2026-03-16
Performance
8k
tokens
662.8
PP tok/s
53.8
TG tok/s
12360
TTFT (ms)
7.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 659.8 63.4 6.8 GB view
4k 729.8 60.7 7.0 GB view
8k 662.8 53.8 7.2 GB current
16k 626.0 52.4 7.7 GB view