← Back to community benchmarks

community:Qwen3.5-9B-OptiQ

M4 (10c) · 32 GB · 4bit · 2026-03-11
Performance
8k
tokens
219.9
PP tok/s
18.6
TG tok/s
37246
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 212.8 19.3 6.6 GB view
4k 221.9 19.1 6.9 GB view
8k 219.9 18.6 7.1 GB current
16k 203.5 17.1 7.6 GB view
32k 186.3 14.7 8.7 GB view
Batching Results
Batch Size TG tok/s Speedup
19.3 1.00×
38.1 1.97×