← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-09
Performance
4k
tokens
1,485
PP tok/s
101.0
TG tok/s
2758
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,465 105.7 6.7 GB view
4k 1,485 101.0 7.0 GB current
8k 1,465 96.2 7.1 GB view
16k 1,413 75.6 7.6 GB view
32k 1,315 50.1 8.7 GB view
64k 1,139 29.4 10.8 GB view
Batching Results
Batch Size TG tok/s Speedup
105.7 1.00×
181.9 1.72×
246.1 2.33×