← Back to community benchmarks

Qwen3.5-9B

M1 Pro (16c) · 32 GB · 4bit · 2026-04-17
Performance
16k
tokens
152.3
PP tok/s
25.5
TG tok/s
107575
TTFT (ms)
7.6
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 16,384
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 view
16k 152.3 25.5 7.6 GB current
Batching Results
Batch Size TG tok/s Speedup
31.2 1.00×
36.2 1.16×
37.8 1.21×