Qwen
Alibaba's open-weight model family, from small to very large.
Why us on this
Qwen models are strong open-weight options across many sizes, including small ones that run on a single GPU. We evaluate them where data must stay on the client's own hardware and a hosted API is ruled out, served through vLLM or Ollama.
More in AI models
The other tools we reach for on the same kind of work.
OpenAI GPTOpenAI
OpenAI's large language models, used through the API.
Runs open-weight language models on your own hardware.
GemmaGoogle
Google's open-weight language models, run on-premise.
High-throughput serving for open-weight models.
Anthropic's Claude models, used through the API and in our own engineering.
Google GeminiGoogle
Google's multimodal models, strong on long documents and images.
xAI's Grok models, available through an API.
Capable open-weight general and reasoning models.
Talk to us
Already running Qwen?
Tell us what it is doing today and where it stops. We will say plainly whether we can move it, what that takes, and when it is the wrong tool for what you are trying to do.
