← Back to community benchmarks

Qwen3.5-9B

M2 Pro (16c) · 32 GB · 4bit · 2026-03-12
Performance
8k
tokens
171.1
PP tok/s
31.8
TG tok/s
47874
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 171.7 35.9 6.7 GB view
4k 172.7 33.9 7.0 GB view
8k 171.1 31.8 7.1 GB current
16k 167.4 26.9 7.6 GB view
Batching Results
Batch Size TG tok/s Speedup
35.9 1.00×
41.1 1.14×
42.3 1.18×