← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-15
Performance
1k
tokens
1,424
PP tok/s
64.1
TG tok/s
719
TTFT (ms)
10.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.10
macOS macOS 15.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,424 64.1 10.7 GB current
4k 1,457 62.1 11.0 GB view
8k 1,443 59.7 11.2 GB view
16k 1,395 54.7 11.7 GB view
Batching Results
Batch Size TG tok/s Speedup
64.1 1.00×
112.0 1.75×
166.8 2.60×
210.1 3.28×