← Back to community benchmarks

Qwen3.5-9B

M5 Max (32c) · 36 GB · 4bit · 2026-03-18
Performance
1k
tokens
2,510
PP tok/s
80.3
TG tok/s
408
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M5 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.2.19.dev1
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,510 80.3 6.7 GB current
4k 2,301 77.2 7.4 GB view
Batching Results
Batch Size TG tok/s Speedup
80.3 1.00×
146.9 1.83×
202.7 2.52×