← Back to community benchmarks

Qwen3.5-9B

M3 Max (40c) · 64 GB · 4bit · 2026-03-09
Performance
4k
tokens
764.4
PP tok/s
67.2
TG tok/s
5358
TTFT (ms)
7.0
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 4,096
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 current
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 view
Batching Results
Batch Size TG tok/s Speedup
67.8 1.00×
103.0 1.52×
128.1 1.89×
150.8 2.22×