← Back to community benchmarks

Qwen3.5-9B

M2 Ultra (60c) · 64 GB · 4bit · 2026-03-12
Performance
8k
tokens
633.7
PP tok/s
83.3
TG tok/s
12928
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 631.7 92.0 6.7 GB view
4k 638.6 88.1 7.0 GB view
8k 633.7 83.3 7.1 GB current
16k 620.0 73.8 7.6 GB view
32k 591.5 59.5 8.7 GB view
64k 538.3 39.8 10.8 GB view
Batching Results
Batch Size TG tok/s Speedup
92.0 1.00×
118.4 1.29×
134.7 1.46×
147.2 1.60×