← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-09
Performance
1k
tokens
361.7
PP tok/s
49.1
TG tok/s
2831
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 361.7 49.1 6.7 GB current
4k 362.3 46.8 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
49.1 1.00×
79.6 1.62×
84.8 1.73×
87.0 1.77×