← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-03-10
Performance
8k
tokens
206.1
PP tok/s
18.6
TG tok/s
39738
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 223.5 19.8 6.5 GB view
4k 219.6 19.3 6.8 GB view
8k 206.1 18.6 7.0 GB current
16k 197.5 17.3 7.5 GB view
Batching Results
Batch Size TG tok/s Speedup
19.8 1.00×
37.3 1.88×
48.2 2.43×
49.8 2.52×