← Back to community benchmarks

Qwen3.5-397B-A17B

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-10
Performance
1k
tokens
413.7
PP tok/s
35.6
TG tok/s
2475
TTFT (ms)
209.6
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 35.6 1.00×
2× 56.6 1.59×
4× 83.6 2.35×
8× 124.5 3.50×