← Back to community benchmarks

Qwen3.5-9B

M5 (10c) · 24 GB · 4bit · 2026-04-15
Performance
8k
tokens
678.1
PP tok/s
24.6
TG tok/s
12081
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.5
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 684.0 25.5 6.3 GB view
8k 678.1 24.6 6.7 GB current
16k 640.9 23.3 7.4 GB view
32k 542.9 20.1 8.9 GB view