← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 32 GB · 4bit · 2026-03-11
Performance
32k
tokens
187.3
PP tok/s
14.4
TG tok/s
174959
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 222.6 18.0 6.5 GB view
8k 213.9 17.2 7.7 GB view
32k 187.3 14.4 9.9 GB current
Batching Results
Batch Size TG tok/s Speedup
18.0 1.00×
38.8 2.16×
53.3 2.96×