← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
8k
tokens
221.0
PP tok/s
19.2
TG tok/s
37076
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 225.1 19.8 6.8 GB view
8k 221.0 19.2 7.0 GB current