← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 8bit · 2026-05-19
Performance
4k
tokens
178.8
PP tok/s
11.2
TG tok/s
22913
TTFT (ms)
10.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 180.7 11.3 9.8 GB view
4k 178.8 11.2 10.4 GB current
8k 174.1 10.7 11.0 GB view
16k 141.2 10.0 11.8 GB view