---
title: "Alibaba's Qwen3.6 Beats GPT-Class Coding Scores Activating Only 3B Parameters"
subtitle: "Alibaba's new open-weight MoE activates only 3B of 35B parameters per token yet hits 73.4% on SWE-bench Verified."
url: "https://alphasignal.ai/news/alibaba-s-qwen3-6-beats-gpt-class-coding-scores-activating-only-3b-parameters"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "Qwen"
company_url: "https://alphasignal.ai/company/alibaba_qwen"
published: "2026-04-16T20:33:03.238Z"
updated: "2026-08-22T02:20:13.079Z"
type: "Model"
topics:
  - "Llms"
  - "Development"
subtopics:
  - "Mixture Of Experts"
  - "Long Context"
  - "Code Agents"
upvotes: 32
source_url: "https://huggingface.co/Qwen/Qwen3.6-35B-A3B"
comments: 0
truncated: true
---

# Alibaba's Qwen3.6 Beats GPT-Class Coding Scores Activating Only 3B Parameters

> Alibaba's new open-weight MoE activates only 3B of 35B parameters per token yet hits 73.4% on SWE-bench Verified.

Alibaba's Qwen team has released [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), an open-weight sparse Mixture of Experts model that punches well above its compute weight class. The multimodal release from Alibaba Cloud carries 35 billion total parameters and activates 3 billion per token, using a hybrid sparse MoE architecture that combines Gated DeltaNet linear attention with standard gated attention layers. Weights ship under Apache 2.0, so you can fine-tune, host, and build products on top of it without a licensing fee.

The headline number has developers paying attention: 73.4% on SWE-bench Verified while activating only 3 billion of its 35 billion parameters per token. For context, Gemma 4-31B, a dense model that activates all 31 billion of its parameters every inference step, scores 52.0% on the same benchmark.

## What A3B actually means for your GPU budget

The naming convention matters. The 35B is the total parameter count sitting in memory, but the router only activates a small fraction for each forward pass. In practice you get the representational capacity of a 35B model at roughly the inference cost of a 3B model, which is why the benchmarks look the way they do.

The internal layout is unusual. Instead of a stack of identical transformer blocks, Qwen3.6 uses a repeating pattern of 10 groups, each containing three Gated DeltaNet layers followed by one Gated Attention layer, all feeding into MoE feed-forward networks. Gated DeltaNet is a linear-attention variant that scales with sequence length far better than softmax attention, which is how the model natively supports a context length of 262,144 tokens, extensible up to 1,010,000 tokens through YaRN scaling. The MoE layer holds 256 experts and routes each token through 8 of them plus 1 shared expert.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [X post by @alphasignal](https://x.com/Qwen/status/2044771299483107739)
- [Qwen/Qwen3.6-35B-A3B on Hugging Face](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
- [Qwen3.6 35B A3B on OpenRouter](https://openrouter.ai/qwen/qwen3.6-35b-a3b)
- [Qwen3.6-35B-A3B: 73.4% SWE-Bench, Runs Locally](https://www.buildfastwithai.com/blogs/qwen3-6-35b-a3b-review)
- [Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All](https://qwen.ai/blog?id=qwen3.6-35b-a3b)