← Back to community benchmarks

Qwen3.5-397B-A17B

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-05
Performance
1k
tokens
456.3
PP tok/s
38.0
TG tok/s
2244
TTFT (ms)
209.6
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 456.3 38.0 209.6 GB current
4k 546.1 36.7 211.3 GB view
8k 545.9 34.7 211.9 GB view
16k 525.1 31.6 213.1 GB view