← Back to community benchmarks

Qwen3.5-9B

M4 Pro (20c) · 48 GB · unknown · 2026-03-10
Performance
4k
tokens
334.2
PP tok/s
2.6
TG tok/s
12258
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 298.4 2.7 22.8 GB view
4k 334.2 2.6 23.0 GB current
Batching Results
Batch Size TG tok/s Speedup
2.7 1.00×
4.4 1.63×
9.1 3.37×