← Back to community benchmarks

Qwen3.5-397B-A17Bvlm

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-30
Performance
1k
tokens
457.3
PP tok/s
38.4
TG tok/s
2239
TTFT (ms)
209.6
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 457.3 38.4 209.6 GB current
8k 545.8 36.6 211.9 GB view
32k 473.2 31.6 216.0 GB view