← Back to community benchmarks

Qwen3.5-9B

M2 (10c) · 16 GB · 4bit · 2026-05-20
Performance
1k
tokens
106.3
PP tok/s
18.8
TG tok/s
9630
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.9rc1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 106.3 18.8 5.7 GB current
4k 108.1 18.2 6.3 GB view
Batching Results
Batch Size TG tok/s Speedup
18.8 1.00×
25.7 1.37×
24.8 1.32×