← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
16k
tokens
124.7
PP tok/s
14.2
TG tok/s
131389
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 178.8 18.4 6.8 GB view
8k 168.5 18.4 7.0 GB view
16k 124.7 14.2 7.5 GB current