← Back to community benchmarks

Qwen3.5-9B

M1 Pro (16c) · 16 GB · 4bit · 2026-03-11
Performance
16k
tokens
142.9
PP tok/s
20.0
TG tok/s
114630
TTFT (ms)
7.6
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.2.7
macOS macOS 15.6
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 155.9 32.5 6.7 GB view
4k 157.3 29.4 7.0 GB view
8k 154.9 19.8 7.1 GB view
16k 142.9 20.0 7.6 GB current
Batching Results
Batch Size TG tok/s Speedup
32.5 1.00×
35.9 1.10×
37.8 1.16×