← Back to community benchmarks

Qwen3.5-9B

M1 Pro (14c) · 32 GB · 4bit · 2026-04-18
Performance
4k
tokens
137.8
PP tok/s
29.2
TG tok/s
29718
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.3.6
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 133.4 30.4 5.8 GB view
4k 137.8 29.2 6.5 GB current
Batching Results
Batch Size TG tok/s Speedup
30.4 1.00×
32.7 1.08×
34.1 1.12×