# Qwen3.5

Alibaba's flagship open model with 397B-A17B MoE architecture, 8.6× decoding improvement over Qwen3, multimodal, 256K context.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: medium
- Recommended workflows: Local or private AI stack
- Permission surface: shell/files, memory
- Agent JSON: https://www.openagent.bot/models/qwen3-5.agent.json

## Summary
Alibaba's flagship open model with 397B-A17B MoE architecture, 8.6× decoding improvement over Qwen3, multimodal, 256K context.

## What It Does
Qwen3.5 is a model in the models category. Alibaba's flagship open model with 397B-A17B MoE architecture, 8.6× decoding improvement over Qwen3, multimodal, 256K context.

## How To Evaluate
Evaluate Qwen3.5 by starting from the official sources, checking its docs, demo interface surface, and running one narrow workflow before expanding scope. Recorded integrations include GitHub, Hugging Face.

## Why It Matters
Qwen3.5 delivers a massive 8.6× decoding speed improvement over Qwen3 with its 397B-A17B MoE architecture, making it one of the most compelling open model families for high-throughput production workloads.


## Best For
- Teams deploying open models at scale with demanding throughput requirements
- Developers evaluating multimodal open models with long-context support
- Builders comparing Qwen3.5 against other MoE architectures for cost-performance tradeoffs

## Not For
- Use cases that require verified safety behavior documentation beyond model card review
- Teams that need a smaller dense model rather than a large MoE architecture

## Fit Matrix
- Local or private AI stack: strong. Qwen3.5 has multiple signals for local or private ai stack, including matching tags, capabilities, category, or positioning. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Browser automation: partial. Qwen3.5 has at least one signal for browser automation, but should be checked against a real task before adoption. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Coding agent workflow: partial. Qwen3.5 has at least one signal for coding agent workflow, but should be checked against a real task before adoption. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Evaluation and observability: partial. Qwen3.5 has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Memory or RAG workflow: partial. Qwen3.5 has at least one signal for memory or rag workflow, but should be checked against a real task before adoption. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Connector or protocol layer: weak. Qwen3.5 is not primarily positioned for connector or protocol layer in the current metadata. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.

## Evidence
- verified: Qwen3.5 is listed as open source. Source: License metadata: Apache-2.0
- verified: Qwen3.5 has a recorded GitHub repository: QwenLM/Qwen3. Source: Resource facts and GitHub source link.
- inferred: Qwen3.5 supports these recorded deployment modes: local, self hosted, cloud. Source: OpenAgent decision signal metadata.
- inferred: Qwen3.5 is tagged with local inference, inference capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/QwenLM/Qwen3

## Facts
- Category: models
- Resource type: model
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-06-16
- GitHub repo: QwenLM/Qwen3
- GitHub stars: 27000

## Capabilities
- local-inference
- inference

## Structured Use Case Tags
- local-ai
- self-hosted-ai

## Links
- GitHub: https://github.com/QwenLM/Qwen3

## Structured Outputs
- JSON: https://www.openagent.bot/models/qwen3-5.json
- Markdown: https://www.openagent.bot/models/qwen3-5.md
- Agent JSON: https://www.openagent.bot/models/qwen3-5.agent.json
- Canonical: https://www.openagent.bot/models/qwen3-5