1T parameters)" },
{ label: "Open licence", value: "Apache 2.0 (Qwen3 series)" },
{ label: "Languages supported", value: "100+" },
]}
/>
Qwen (also rendered as Tongyi Qianwen, 通义千问) is a family of large language models developed by Alibaba Cloud. The series spans small open-weight dense models suitable for edge deployment through to proprietary trillion-parameter mixture-of-experts systems served via the Alibaba Cloud Model Studio platform. Qwen is one of the most actively maintained open-weight model families and a primary alternative to Llama, Mistral, and DeepSeek in the open ecosystem.
The first generation, Qwen-7B, was released in August 2023 under a permissive licence and was followed by progressively larger and more capable releases through 2024. The Qwen2 series introduced grouped-query attention, longer context windows, and dedicated math and code variants. The Qwen3 series, released in April 2025, includes dense models at 0.6B, 1.7B, 4B, 8B, 14B, and 32B parameters and mixture-of-experts variants at 30B (3B active) and 235B (22B active). All Qwen3 models support a unified "thinking" and "non-thinking" inference mode that allows the same checkpoint to either reason step by step or respond directly.
Architecture and capabilities
Qwen models follow a decoder-only transformer design with refinements borrowed from contemporary research: rotary position embeddings, SwiGLU activation, RMSNorm, and grouped-query attention. Larger variants adopt sparse mixture-of-experts layers. Tokenisation uses a byte-pair encoding vocabulary tuned for Chinese, English, and major Asian languages.
The Qwen3 generation was trained on approximately 36 trillion tokens drawn from web text, code, mathematics, and synthetic reasoning traces. Alibaba reports improvements across mathematics, coding, logical reasoning, instruction following, and tool use, with the model series leading several open benchmarks at the time of release. Native support for over 100 languages includes Bahasa Malaysia, Bahasa Indonesia, Thai, Vietnamese, and Tagalog, which has driven adoption in Southeast Asia.
Qwen3-Max and long context
Qwen3-Max is the proprietary flagship of the family, with more than one trillion parameters and a context window extended to 256K tokens in standard configuration. A long-context variant, Qwen3-Instruct-2507, supports inputs of up to one million tokens, placing it among the longest production-deployed context windows alongside Gemini 1.5 and Claude Sonnet 4. Qwen3-Max is served only via the Alibaba Cloud API and has ranked in the top three of the LMArena public evaluation leaderboard.
| Model | Total params | Active params | Context | Licence |
|---|---|---|---|---|
| Qwen3-0.6B | 0.6B | 0.6B | 32K | Apache 2.0 |
| Qwen3-8B | 8B | 8B | 128K | Apache 2.0 |
| Qwen3-32B | 32B | 32B | 128K | Apache 2.0 |
| Qwen3-30B-A3B | 30B | 3B | 128K | Apache 2.0 |
| Qwen3-235B-A22B | 235B | 22B | 128K | Apache 2.0 |
| Qwen3-Max | >1T | undisclosed | 256K-1M | Proprietary |
Specialised variants
The Qwen family includes specialised checkpoints for coding (Qwen-Coder), mathematics (Qwen-Math), and vision-language understanding (Qwen-VL). The Qwen2.5-VL release covers image and video reasoning, document parsing, and grounded perception, and Qwen2.5-Omni adds speech understanding and generation. These variants are commonly used as base models for fine-tuning by third parties.
Qwen has emerged as a primary base model for Bahasa Malaysia and code-switched Malay-English fine-tuning work in Malaysia, in part because its tokeniser handles non-Latin and Southeast Asian scripts more efficiently than Llama or Mistral. Academic groups at Universiti Malaya, Universiti Kebangsaan Malaysia, and Universiti Sains Malaysia have published on Qwen-derived models for Bahasa Malaysia summarisation, sentiment analysis, and government document understanding.
Cloud availability is supported through Alibaba Cloud regions, which operate a data centre in Malaysia. The Malaysian Communications and Multimedia Commission (MCMC) and the Malaysia Digital Economy Corporation (MDEC) have engaged with Alibaba Cloud under the Digital Free Trade Zone (DFTZ) framework. Several Malaysian e-commerce, logistics, and customer-service operators — including those serving Shopee and Lazada Malaysia partners — use Qwen via Alibaba Cloud Model Studio.
For regulated sectors, Bank Negara Malaysia (BNM) Risk Management in Technology (RMiT) policy and Personal Data Protection Act (PDPA) compliance push firms to self-host open-weight Qwen models on domestic infrastructure provided by TM ONE, AIMS Cyberjaya, or YTL Data Center. The MyDIGITAL Corporation and the National AI Office (launched December 2024) list Qwen among the open foundation models considered for sovereign AI capability.
Government interest extends to Qwen multilingual capability for serving Bahasa Malaysia, Mandarin, Tamil, and English populations through a single inference stack — a requirement for many Malaysian government digital services covered by the JPN, LHDN, and MyGov portals.
- Qwen Team, Alibaba Cloud. (2024). Qwen2 Technical Report. arXiv:2407.10671.
- Qwen Team. (2025). Qwen3 Technical Report. arXiv:2505.09388.
- Alibaba Cloud. (2025). Alibaba Introduces Qwen3, Setting New Benchmark in Open-Source AI with Hybrid Reasoning. Alibaba Cloud Community.
- Malaysia Digital Economy Corporation. (2024). National AI Roadmap and Foundation Model Landscape. MDEC publications.