← Back to community benchmarks

Qwen3.5-9B

M5 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
1k
tokens
1,930
PP tok/s
100.1
TG tok/s
531
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,930 100.1 5.8 GB current
4k 2,863 99.0 6.5 GB view
8k 2,730 91.5 6.9 GB view
16k 2,403 90.1 7.9 GB view
32k 2,079 76.4 9.7 GB view
Batching Results
Batch Size TG tok/s Speedup
100.1 1.00×
160.4 1.60×
216.2 2.16×