← Back to community benchmarks

Qwen3.5-9B

M1 Pro (14c) · 32 GB · 4bit · 2026-03-09
Performance
1k
tokens
137.8
PP tok/s
30.2
TG tok/s
7430
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 137.8 30.2 6.7 GB current
4k 138.2 27.9 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
30.2 1.00×
20.8 0.69×
33.8 1.12×