← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 4bit · 2026-07-17
Performance
4k
tokens
188.0
PP tok/s
19.2
TG tok/s
21784
TTFT (ms)
6.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.4.4rc1
macOS macOS 26.5.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 188.0 19.2 6.2 GB current
16k 180.5 18.9 7.4 GB view
64k 135.2 12.1 12.6 GB view