← Back to community benchmarks

Qwen3.5-397B-A17B

M3 Ultra (80c) · 512 GB · 6bit · 2026-03-08
Performance
4k
tokens
487.1
PP tok/s
27.2
TG tok/s
8409
TTFT (ms)
302.9
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 15.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 454.0 28.5 302.7 GB view
4k 487.1 27.2 302.9 GB current
8k 484.9 26.0 303.3 GB view
16k 462.0 23.6 304.0 GB view
32k 422.5 20.2 305.5 GB view
Batching Results
Batch Size TG tok/s Speedup
28.5 1.00×
44.3 1.55×
57.9 2.03×
81.5 2.86×