← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-13
Performance
4k
tokens
1,460
PP tok/s
62.4
TG tok/s
2805
TTFT (ms)
11.0
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.10
macOS macOS 15.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,423 64.5 10.7 GB view
4k 1,460 62.4 11.0 GB current
Batching Results
Batch Size TG tok/s Speedup
64.5 1.00×
110.7 1.72×
164.7 2.55×