← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 32 GB · 4bit · 2026-03-18
Performance
16k
tokens
175.9
PP tok/s
18.2
TG tok/s
93148
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.18
macOS macOS 15.7.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 188.6 21.4 6.5 GB view
4k 190.4 20.5 7.3 GB view
8k 186.3 19.9 7.7 GB view
16k 175.9 18.2 8.4 GB current
Batching Results
Batch Size TG tok/s Speedup
21.4 1.00×
40.9 1.91×
43.2 2.02×
44.8 2.09×