← Back to community benchmarks

Qwen3.5-9B

M2 Ultra (76c) · 128 GB · 6bit · 2026-03-08
Performance
64k
tokens
653.8
PP tok/s
39.8
TG tok/s
100232
TTFT (ms)
12.7
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 128 GB
GPU Cores 76
Software
oMLX v0.2.6
macOS macOS 26.3
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 775.8 74.3 8.7 GB view
4k 783.9 72.1 8.9 GB view
8k 776.7 68.7 9.2 GB view
16k 758.8 62.8 9.6 GB view
32k 724.1 52.6 10.6 GB view
64k 653.8 39.8 12.7 GB current
Batching Results
Batch Size TG tok/s Speedup
74.3 1.00×
103.6 1.39×
122.3 1.65×
137.0 1.84×