← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 4bit · 2026-03-10
Performance
8k
tokens
109.4
PP tok/s
12.3
TG tok/s
74858
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 185.8 19.9 6.5 GB view
4k 165.7 16.8 6.8 GB view
8k 109.4 12.3 7.0 GB current
16k 100.3 14.7 7.5 GB view
32k 107.6 7.6 8.5 GB view
Batching Results
Batch Size TG tok/s Speedup
19.9 1.00×
19.5 0.98×
20.4 1.03×
26.7 1.34×