← Inference Inference · Qwen 4

Qwen 4.0 27B,
on a GPU of your own, once it ships.

Qwen has not published the Qwen 4.0 27B weights yet. When it does, we read the published files, work out which of our machines it fits, and serve it with vLLM behind an OpenAI-compatible /v1 endpoint — one tenant per GPU, in Poland.

What is known

The model filled in from the weights on release
Developer
Alibaba Qwen
Parameters
not published yet
Context
not published yet
Licence
not published yet
Weight formats
not published yet
Which GPU fits
computed from config.json on release
Qwen on Hugging Face →
How it will be served same as every model here
Endpoint
OpenAI-compatible /v1 — chat, completions, streaming.
Engine
vLLM, the weight format that fits your context needs.
Tenancy
One customer per GPU — nobody else’s requests run on it.
Location
Poland, EU — on machines we own and run.
Billing
Per hour of GPU time, USD + VAT. Rate set once the model ships.

Want Qwen 4.0 27B the week it ships?

Write what load you expect and how much context you need — you hear from us as soon as the weights are out. Reply within one business day.

hello@robertz.co

Not open yet

We are checking the demand.

We are collecting interest to see whether there is demand to open this service. Let us know you want it, so we open sooner :)

Let us know