← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 32 GB · 4bit · 2026-03-11
Performance
8k
tokens
209.7
PP tok/s
18.3
TG tok/s
39074
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 222.3 21.4 6.5 GB view
4k 218.9 19.0 6.8 GB view
8k 209.7 18.3 7.0 GB current
16k 212.2 17.2 7.5 GB view
32k 189.9 13.7 8.5 GB view
Batching Results
Batch Size TG tok/s Speedup
21.4 1.00×
38.2 1.79×
50.0 2.34×
51.4 2.40×