← Back to community benchmarks

Qwen3.5-9B

M5 Pro (20c) · 24 GB · 4bit · 2026-03-18
Performance
16k
tokens
1,535
PP tok/s
48.2
TG tok/s
10674
TTFT (ms)
8.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 24 GB
GPU Cores 20
Software
oMLX v0.2.18
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,593 56.9 6.7 GB view
4k 1,640 55.1 7.4 GB view
8k 1,629 53.4 7.8 GB view
16k 1,535 48.2 8.6 GB current
Batching Results
Batch Size TG tok/s Speedup
56.9 1.00×
105.4 1.85×
140.3 2.47×
149.8 2.63×