Qwen's distinguishing feature is range. It ships across one of the widest ranges of sizes of any open family, which means the same architecture and tokeniser can serve a phone, a single GPU and a multi-node cluster — and that consistency is worth more in a real system than it sounds.
All Model Families →
Provider-published specifications as of 1 September 2026, not figures we measured. Model families move quickly — check the provider's own documentation before committing to a number.
Most production AI systems end up wanting more than one model. A small one for classification and routing, a mid-size one for the bulk of the work, a large one for the hard minority of requests. Assembling that from three different families means three tokenisers, three prompt idioms, three evaluation baselines and three sets of quirks to learn.
Qwen's range lets you build that ladder inside one family. Prompts transfer with far less rework, an evaluation harness written for one size largely holds for another, and when you move a request class from the mid-size model to the small one — which is where a great deal of cost saving actually comes from — you are changing a parameter rather than rewriting an integration.
The multilingual coverage is the second reason we reach for it. If your corpus contains Chinese, Japanese or Korean alongside European languages, this family has, in our evaluations, handled the mix better than Western-trained alternatives of comparable size, and the difference shows up immediately on a fair evaluation set rather than needing a subtle one.
Qwen is developed by Alibaba, and the assessment is structurally the same one we set out on the DeepSeek page: separate the transfer question from the behaviour question from the artefact question. Self-hosting closes the first completely — the weights are a file and they transmit nothing. The second is testable on your own material and is workload-dependent. The third is only partially answerable, for every model from every jurisdiction.
Where an organisation has a standing policy against models of Chinese origin, that policy is the answer and we build with Mistral or Llama, which occupy adjacent ground. It is a governance decision owned by people who own the risk, and it is not our place to argue anyone out of it.
Where the deployment is a single size on a single class of hardware, the size ladder stops being an advantage and the decision comes down to capability and tooling on that one rung — which is frequently where Llama's deeper serving ecosystem wins.
Where the workload is at the hardest end of agentic or reasoning work, the leading proprietary models still lead, and a hybrid arrangement that routes that minority out is usually better than choosing one family for everything. See hybrid model routing.
At most sizes, yes — and its small models in particular are strong relative to their footprint, which is exactly where a lot of production value sits. As always the comparison that matters is on your task, and we run it rather than argue about it.
The lower rungs of the ladder run comfortably on a single accelerator, and the smallest run on a CPU at usable speeds for batch work. That makes them a realistic option for edge deployments and for on-premise setups where a full GPU node is not justified.
Write it down before you build. Record which model and version you deployed, where it runs, what the licence permits, what evaluation you ran on sensitive-topic behaviour, and who signed it off. That record is what turns a defensible decision into an evidenced one, and it takes an afternoon.
We will build the routing ladder and show you what moves down a rung without losing quality.
30-minute technical call · no deck
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Apps, platforms and campaigns for these teams, long before the AI work. Every one is written up on the work page — what we did, and where our part ended.
