Qwen3.5 397B-A17B

Find hardware that runs Qwen3.5 397B-A17B on your budget

Reference: Model card on Hugging Face

Parameters
403.4 B
Active per token
17 B
Architecture
MoE
Modality
vision
Max context
1010000
Released
2026-02-16
License
apache-2.0

Measurements

Decode is token generation — the speed you feel while an answer streams. Prefill is prompt processing — the wait before it starts. Why bandwidth predicts decode speed.

What verified, single-source and estimated mean, and the same rows with every filter and sort in the benchmarks explorer.

Speed over time

Cheapest hardware by target speed

The lowest-priced entry that reaches each threshold, using the strongest evidence available. Estimated rows are marked.