---
name: 'Qwen3.5:397B'
slug: qwen-3-5397b
type: Multimodal
providers:
  - ollama-cloud
description: 'Qwen vision-language model for visual reasoning, documents, and agent tasks'
tags:
  - open-source
  - reasoning
  - tool-use
  - multimodal
  - qwen
is_open_source: true
context_window: 262144
max_output: 65536
release_date: '2026-02-15'
capabilities:
  audio: false
  vision: true
  tool_use: true
  citations: false
  reasoning: true
---
Qwen3.5:397B is a Multimodal model.
Qwen vision-language model for visual reasoning, documents, and agent tasks