← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-11
Performance
1k
tokens
1,359
PP tok/s
57.0
TG tok/s
754
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.8
macOS macOS 15.6
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,359 57.0 6.7 GB current
4k 1,406 52.7 6.8 GB view
8k 1,406 55.2 7.1 GB view
16k 1,368 55.8 7.6 GB view
32k 1,272 39.6 8.7 GB view
64k 1,085 27.5 10.8 GB view
Batching Results
Batch Size TG tok/s Speedup
57.0 1.00×
113.8 2.00×
220.3 3.86×
292.2 5.13×