← Back to community benchmarks

Qwen3.5-9B

M3 Max (40c) · 64 GB · 4bit · 2026-03-09
Performance
64k
tokens
523.0
PP tok/s
35.8
TG tok/s
125319
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 744.7 67.8 6.7 GB view
4k 764.4 67.2 7.0 GB view
8k 735.0 61.7 7.1 GB view
16k 625.5 53.6 7.6 GB view
32k 600.8 47.4 8.7 GB view
64k 523.0 35.8 10.8 GB current
Batching Results
Batch Size TG tok/s Speedup
67.8 1.00×
103.0 1.52×
128.1 1.89×
150.8 2.22×