← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
16k
tokens
209.3
PP tok/s
17.9
TG tok/s
78297
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.6.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 221.0 19.5 7.0 GB view
16k 209.3 17.9 7.5 GB current