---
title: "Qwen3.6 35B A3B API hosted in the EU"
description: "Run Qwen3.6 35B A3B on inference.eu: a fast mixture-of-experts model with 3B active parameters, image input and 256K context, processed in the EU."
canonical: "https://inference.eu/models/qwen3-6-35b-a3b/"
language: "en"
---

Code · Qwen (Alibaba Cloud)

# Run Qwen3.6 35B A3B in the EU through an OpenAI-compatible API

Qwen3.6 35B A3B is the mixture-of-experts member of Alibaba's Qwen3.6 family: 35 billion parameters, only about 3 billion active per token, with image input, a thinking mode and 256K tokens of context. On inference.eu you call it with the OpenAI or Anthropic request format, processed in EU data centres and never used for training.

[Contact sales](https://inference.eu/contact/)[Example request](#example)

1.  0135B · 3B
2.  02EU data centres
3.  03Apache 2.0

## What Qwen3.6 35B A3B is

Qwen3.6 35B A3B was the first open-weight Qwen3.6 model, released in April 2026 under Apache 2.0. It has 35 billion parameters in total and about 3 billion active for each token, with a vision encoder for image input. Its 40 layers combine Gated DeltaNet linear attention and gated attention, each followed by a mixture-of-experts block.

The native context window is 262,144 tokens, extendable to about one million according to Qwen. Like the dense Qwen3.6 27B, it focuses on agentic coding, front-end work and repository-level reasoning, and supports thinking preservation, which keeps reasoning from earlier turns available in long sessions.

## What it does well, and where it falls short

With only about 3 billion active parameters, this model answers fast and handles high request volumes efficiently, while still offering image input, tool calls and a long context. It works well for coding autocomplete-style help, quick agent steps, triage of screenshots and bulk text processing where a dense model would be slower.

The small active size has a cost: on harder reasoning, long code changes and nuanced writing, the dense Qwen3.6 27B or Qwen3.8 27B give better answers. Qwen advises keeping at least 128K tokens of context free for the thinking mode. For production-critical outputs, compare it against a larger model on a sample of real requests.

## Calling Qwen3.6 35B A3B through the API

inference.eu uses the OpenAI request format, so the OpenAI SDKs, LangChain, LlamaIndex and coding tools work unchanged. Set the base URL to the inference.eu API, use your inference.eu key and set the model to `qwen3.6-35b-a3b`. The Anthropic Messages format is also available.

Thinking is on by default; pass `enable_thinking: false` in `chat_template_kwargs` through `extra_body` for direct answers, which suits high-volume tasks. Pass `preserve_thinking: true` to keep earlier reasoning in multi-turn sessions. Send images as `image_url` content parts. Because the request format is shared across models, switching to Qwen3.6 27B means changing only the model string.

## Data residency for Qwen3.6 35B A3B

On inference.eu, Qwen3.6 35B A3B runs on infrastructure in the European Union. Prompts, images, code and responses are processed in EU data centres, are not sent to Alibaba in China, and are never used to train any model.

Every customer receives a data processing agreement under Article 28 of the GDPR and our list of subprocessors, so your records of processing can name every party involved. Billing is in euros, on one invoice across all models. The Apache 2.0 licence allows commercial use without user limits or revenue thresholds.

## Qwen3.6 35B A3B

Maker

Qwen (Alibaba Cloud)

Made in

China

Type

Code

Parameters

35B

Active parameters

3B

Context window

262,144 tokens

Licence

[Apache 2.0](https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE)

Released

April 2026

Model ID

qwen3.6-35b-a3b

Processing

EU data centres

Training on your data

Never

Source

[huggingface.co](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)

qwen3.6-35b-a3b · Python

```
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inference.eu/v1", api_key=os.environ["INFERENCE_EU_API_KEY"])

response = client.chat.completions.create(
    model="qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": "Summarise this contract in five bullet points."}],
)
print(response.choices[0].message.content)
```

## What teams use it for

-   1

    ### Fast coding help

    Answer short code questions and suggest edits quickly inside an editor or chat tool.

-   2

    ### Bulk text processing

    Classify, summarise or extract data from large volumes of tickets, emails or logs at low cost per request.

-   3

    ### Quick agent steps

    Handle the simple steps of an agent workflow, such as lookups and routing, and leave hard steps to a larger model.

## Qwen3.6 35B A3B: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Compliance depends on how you process data. On inference.eu, requests are processed in EU data centres, not used for training and covered by a data processing agreement under Article 28 GDPR with a published subprocessor list. Nothing is sent to Alibaba or to China.

A3B means about 3 billion active parameters. The model has 35 billion parameters in total, split into experts, but only around 3 billion work on each token. That makes generation much faster than a dense model of the same total size.

The native context window is 262,144 tokens, and Qwen describes ways to extend it to about one million. For thinking mode, Qwen advises keeping at least 128K tokens of context available to preserve reasoning quality.

Yes. It is released under the Apache 2.0 licence, which allows commercial use, modification and redistribution without fees or user limits. You do not need an agreement with Alibaba to use it in paid products.

Use 35B A3B when speed and volume matter: it uses roughly a ninth of the active compute per token. Use the dense 27B when answer quality on harder coding and reasoning matters more. Both share context length, image input and thinking options.

Yes. It includes a vision encoder and reads screenshots, diagrams and documents together with text, answering in text. Send images in the standard OpenAI \`image\_url\` format alongside your question. It cannot generate images.

Pass \`enable\_thinking: false\` inside \`chat\_template\_kwargs\` in the request's \`extra\_body\`. The model then answers directly without a reasoning block, which is faster and cheaper for simple, high-volume tasks such as classification.

Both are mixture-of-experts models with few active parameters, image input and 256K context. Qwen3.6 35B A3B leans towards agentic coding and has thinking preservation; Gemma 4 26B A4B is a general-purpose model from Google. Test both on your real traffic.

On inference.eu the open weights run in EU data centres, so your data does not go to Alibaba or to China. The model's training still reflects its maker's choices, including on politically sensitive topics. Test it on your own prompts before production use.

Change the base URL of your OpenAI client to the inference.eu API, use your inference.eu key and set the model to \`qwen3.6-35b-a3b\`. Messages, images, tools and streaming keep working with your existing code.

[Ask a question](https://inference.eu/contact/)

## Related

[All models](https://inference.eu/models/#directory)

-   [Qwen3.6 27BRun Qwen3.6 27B on inference.eu: a dense open model for agentic coding with image input and 256K context, OpenAI-compatible and processed in the EU.Code](https://inference.eu/models/qwen3-6-27b/)
-   [Gemma 4 26B A4BRun Google's Gemma 4 26B A4B on inference.eu: a fast mixture-of-experts model with image input and 256K context, processed in EU data centres.Vision](https://inference.eu/models/gemma-4-26b-a4b/)
-   [gpt-oss-20bRun OpenAI's compact open-weight gpt-oss-20b reasoning model on inference.eu: the OpenAI API format, processed in EU data centres, billed in euros.Reasoning](https://inference.eu/models/gpt-oss-20b/)
-   [Qwen3.8 27BRun Qwen3.8 27B on inference.eu: a dense open model with image and video input, adjustable reasoning and 256K context, OpenAI-compatible, processed in the EU.Reasoning](https://inference.eu/models/qwen3-8-27b/)

## Move your AI workloads to EU infrastructure

Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps.

-   Reply within one working day
-   Pricing for your volume
-   DPA ready to sign