Dedicated model · Available as managed deployment

Request a Qwen3-VL deployment on your own DGX Spark

Qwen's vision-language models — 2B, 4B and 8B — that read images, screenshots, documents and video alongside text, under Apache-2.0. Validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.

eu-es-1 · Málaga Available as managed deployment Text + vision Quoted per deployment qwen3-vl.axforge.ai
Request deploymentTalk to an engineerSign in €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT Hardware rental plus a managed service quoted per deployment — both confirmed in writing before anything is billed.

Why AxForge

Why Qwen3-VL as a managed deployment

Sees what you sendScreenshots, scans, charts, photos and video frames — Qwen3-VL answers about them in text, with strong document and OCR-style understanding.
Small enough to be fastThe 8B is a full vision-language model on a single dedicated DGX Spark; the 2B and 4B are for high-volume image tasks.
Apache-2.0Permissive weights — deploy on your own hardware and ship commercially without a licence conversation.

Specifications

What you get

ModelQwen3-VL — Qwen
ModalitiesText + vision — accepts image input
Sizes2.1B, 4.4B, 8.8B
LicenceOpen weights — apache-2.0; commercial use permitted
HardwareNVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge
Rental termHour, week, month or year
Hardware pricing€0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT
Managed serviceQuoted per deployment
RegionMálaga, Spain (eu-es-1)

Full details, benchmarks and FAQ on the Qwen3-VL page. Prices exclude VAT.

How it works

From sign-in to running

1Request deployment — describe your traffic, context needs and rental term.
2You receive the configuration, hardware rental and managed-service price in writing before anything is billed.
3AxForge deploys Qwen3-VL on a dedicated DGX Spark reserved for you.
4Point your OpenAI SDK at your own endpoint with the model name you receive.
5Adjust the term — hour, week, month or year — as your workload settles.

Request deployment or sign in to start.

FAQ

Qwen3-VL — common questions

Is Qwen3-VL on the AxForge serverless API?

Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.

What can Qwen3-VL do with images?

Describe them, answer questions about them, read text in them, extract fields from documents and forms, and reason over charts and UI screenshots.

Which Qwen3-VL size should I deploy?

8B for quality, 2B or 4B for throughput — all three run on a dedicated DGX Spark behind the same OpenAI-compatible endpoint.

How fast is it on your hardware?

AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.

What does EU Qwen3-VL hosting cost?

Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.

Ready for Qwen3-VL on your own machine?

Request deployment Sign in Talk to an engineer

Explore

More from AxForge

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms