← Back to community benchmarks

Qwen3.5-9B

M5 (10c) · 32 GB · 8bit · 2026-07-19
Performance
16k
tokens
659.9
PP tok/s
12.3
TG tok/s
24829
TTFT (ms)
11.6
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.5.2.dev1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 659.9 12.3 11.6 GB current
32k 569.2 11.4 13.1 GB view
64k 447.8 9.9 16.2 GB view