← Back to community benchmarks

Qwen3.5-9B

M5 (8c) · 16 GB · 4bit · 2026-05-18
Performance
1k
tokens
571.7
PP tok/s
27.9
TG tok/s
1791
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M5 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.8
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 571.7 27.9 5.7 GB current
4k 620.5 27.2 6.3 GB view
Batching Results
Batch Size TG tok/s Speedup
27.9 1.00×
52.0 1.86×
55.4 1.99×