← Back to community benchmarks

Qwen3.5-9B

M1 Pro (16c) · 16 GB · 4bit · 2026-03-12
Performance
1k
tokens
121.4
PP tok/s
27.8
TG tok/s
8433
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.2.9
macOS macOS 15.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 121.4 27.8 6.7 GB current
4k 131.1 30.6 7.0 GB view
8k 153.3 27.3 7.1 GB view
Batching Results
Batch Size TG tok/s Speedup
27.8 1.00×
36.4 1.31×