DEV.co
AI Frameworks · QwenLM

Qwen

Qwen is Alibaba Cloud's open-source large language model series, available in sizes from 1.8B to 72B parameters, with both base and chat-aligned variants. Models support 32K context length, multilingual training (Chinese and English focus), and come in multiple quantization formats (Int4, Int8) for reduced memory footprint.

Source: GitHub — github.com/QwenLM/Qwen
21.4k
GitHub stars
1.8k
Forks
Python
Primary language
Apache-2.0
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
RepositoryQwenLM/Qwen
OwnerQwenLM
Primary languagePython
LicenseApache-2.0 — OSI-approved
Stars21.4k
Forks1.8k
Open issues41
Latest releaseUnknown
Last updated2026-03-05
Sourcehttps://github.com/QwenLM/Qwen

What Qwen is

Qwen comprises pretrained base models and instruction-tuned chat models trained on 2.2–3T multilingual tokens, featuring flash-attention optimization, configurable context windows (8K–32K), quantization support (GPTQ, KV cache, Int4/Int8), and tool-use capabilities. Inference memory requirements range from 2.9GB (1.8B Int4) to 48.9GB (72B Int4) for 2048-token generation.

Quickstart

Get the Qwen source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/QwenLM/Qwen.gitcd Qwen# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Chinese-optimized NLP pipelines

Strong performance on Chinese language tasks (chat, summarization, translation, QA) with native support for 32K context and system prompt enhancements in larger models.

Memory-constrained deployments

Int4 and Int8 quantized variants enable inference on modest hardware (2.9GB for 1.8B); Q-LoRA fine-tuning support reduces VRAM for adaptation on consumer-grade GPUs.

Tool-augmented agents and code interpretation

All models support tool use; documentation references agent framework and code interpreter capabilities suitable for autonomous task automation.

Implementation considerations

  • Select model size (1.8B–72B) and quantization (full-precision, Int8, Int4) based on latency, memory, and accuracy trade-offs; document GPU/CPU requirements upfront.
  • Qwen2 is the active successor; evaluate migration path early if planning long-term support—Qwen1 codebase divergence may complicate future transitions.
  • Fine-tuning via full-parameter, LoRA, or Q-LoRA; verify Q-LoRA VRAM overhead (5.8GB–61.4GB minimum) aligns with your infrastructure before committing.
  • Integrate models via Hugging Face/ModelScope APIs, or build custom OpenAI-compatible API wrappers using provided examples and deployment guides.
  • Test context window performance (8K for 14B, 32K for 1.8B/72B) against your workload; long-context evaluation data available in repository.

When to avoid it — and what to weigh

  • Require active upstream maintenance and frequent updates — Repository explicitly states 'no longer actively maintained' in favor of Qwen2; expect minimal bug fixes and feature additions to this codebase.
  • Need extensive English-language benchmarks and western domain coverage — Model trained with heavy focus on Chinese and English; limited information on performance outside these languages or on specialized western domains.
  • Require commercial support or SLA guarantees — Community-supported open-source project; no mention of professional support tiers, incident response, or liability indemnification.
  • Cannot tolerate dependency on Alibaba Cloud infrastructure — Primary hosting and API services tied to Alibaba (DashScope API, ModelScope); self-hosting required for air-gapped environments.

License & commercial use

Apache License 2.0 (Apache-2.0). Permissive OSI-approved license allowing commercial use, modification, and distribution with attribution and liability disclaimer. Model weights and code both licensed identically.

Apache-2.0 permits commercial deployment and monetization without royalties. However, verify no export restrictions apply (model is Chinese-origin; check your jurisdiction). Conduct security/bias review before production use. No warranty or indemnification provided; liability rests with deployer. Consider obtaining legal counsel for high-stakes applications.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceStale
DocumentationAdequate
License clarityClear
Deployment complexityModerate
DEV.co fitGood
Assessment confidenceHigh
Security considerations

No third-party security audit or vulnerability disclosure program mentioned. Model trained on internet-scale data; standard LLM risks (prompt injection, jailbreak) apply. No guardrails mentioned beyond training alignment. Verify output safety for sensitive domains. Self-hosting avoids Alibaba Cloud data exposure, but requires your own infrastructure security hygiene. No rate-limiting or access control documented for inference.

Alternatives to consider

Llama 2 / Llama 3 (Meta)

Larger ecosystem, active maintenance, stronger English performance. Llama 2 Apache-2.0 licensed. Heavier (~70B model) but broader community adoption and tooling.

Mistral 7B / Mixtral (Mistral AI)

Smaller footprint, faster inference, well-maintained. Apache-2.0 licensed. Lower resource overhead and newer architecture, but less mature for Chinese NLP.

Qwen2 (QwenLM/Qwen2)

Official successor to Qwen1; actively maintained, same licensor. Better performance and ongoing support. If starting new project, Qwen2 recommended over this codebase.

Software development agency

Build on Qwen with DEV.co software developers

Evaluate your use case, model size, and infrastructure. Consider Qwen2 for new projects. Start with quantized variants to reduce memory overhead. Test migration if upgrading from Qwen1.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

Qwen FAQ

Is Qwen production-ready?
Qwen1 is feature-complete but no longer actively maintained; Qwen2 is the recommended path forward. For new projects, prefer Qwen2. For existing Qwen1 deployments, test migration or accept community-only support.
Can I use Qwen commercially?
Yes, Apache-2.0 permits commercial use without royalties. However, verify no export or sanctions restrictions apply to your jurisdiction. Review model safety and bias before production deployment.
What are the minimum hardware requirements?
1.8B Int4 model requires ~2.9GB VRAM for inference. 72B full-precision requires ~144GB+. Quantization (Int4/Int8) substantially reduces footprint. Q-LoRA fine-tuning on 1.8B needs ~5.8GB.
Does Qwen support long-context tasks?
Yes: 1.8B, 72B support 32K context; 7B and 14B support 8K and 32K respectively. Context extension via rotary positional embeddings. Evaluation data provided in repository.

Custom software development services

Need help beyond evaluating Qwen? DEV.co is a software development agency offering software development services and web development for teams of every size. Our software developers and web developers build custom software, web applications, APIs, and ai frameworks integrations — and maintain them long-term.

Ready to Deploy Qwen?

Evaluate your use case, model size, and infrastructure. Consider Qwen2 for new projects. Start with quantized variants to reduce memory overhead. Test migration if upgrading from Qwen1.