← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 32 GB · 4bit · 2026-03-11
Performance
32k
tokens
189.9
PP tok/s
13.7
TG tok/s
172524
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 32,768
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 view
16k 212.2 17.2 7.5 GB view
32k 189.9 13.7 8.5 GB current
Batching Results
Batch Size TG tok/s Speedup
21.4 1.00×
38.2 1.79×
50.0 2.34×
51.4 2.40×