← Back to community benchmarks

Qwen3.5-9B

M4 Pro (20c) · 64 GB · bf16 · 2026-04-17
Performance
32k
tokens
406.5
PP tok/s
13.2
TG tok/s
80617
TTFT (ms)
20.9
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 442.6 15.1 17.5 GB view
4k 488.5 14.8 18.3 GB view
8k 458.0 14.1 18.7 GB view
16k 420.5 13.9 19.5 GB view
32k 406.5 13.2 20.9 GB current
64k 378.2 11.9 24.1 GB view
128k 300.9 8.4 30.5 GB view
195k 241.6 6.8 37.0 GB view