← Back to community benchmarks

Qwen3.5-9B

M1 Pro (16c) · 32 GB · 4bit · 2026-04-17
Performance
8k
tokens
155.5
PP tok/s
29.4
TG tok/s
52674
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 150.1 31.2 5.8 GB view
8k 155.5 29.4 6.9 GB current
16k 152.3 25.5 7.6 GB view
Batching Results
Batch Size TG tok/s Speedup
31.2 1.00×
36.2 1.16×
37.8 1.21×