← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 4bit · 2026-07-17
Performance
64k
tokens
135.2
PP tok/s
12.1
TG tok/s
484761
TTFT (ms)
12.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.4.4rc1
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 188.0 19.2 6.2 GB view
16k 180.5 18.9 7.4 GB view
64k 135.2 12.1 12.6 GB current