AxForge offering · Request
Alibaba's Qwen3 family of dense models from 0.6B to 32B and mixture-of-experts up to 235B, with a switchable thinking mode, 119 languages and Apache-2.0 weights. Validated on AxForge hardware with a dedicated DGX Spark deployment option for your traffic only, subject to confirmed availability, configuration and licence, as an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Currently request-only. Add your request to the public forum; this is not a booking or a promised launch.
Why AxForge
| One family, every size | 0.6B to 32B dense plus 30B-A3B and 235B-A22B MoE: pick the size for the job and keep the same behaviour and prompt style across them. |
|---|---|
| Thinking on demand | Qwen3 reasons step by step when you ask and answers directly when you do not. One model for both modes, switched per request. |
| Apache-2.0 | Permissive weights with no usage conditions: deploy, fine-tune and ship commercially without a licence conversation. |
Specifications
| Model | Qwen3 by Qwen |
|---|---|
| Modalities | Text |
| Sizes | 752M, 1.7B, 2.0B, 4.0B, 8.2B, 14.8B |
| Context window | 40,960 tokens |
| Licence | Open weights (apache-2.0); commercial use permitted |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Rental term | Hour, week, month or year |
| Hardware pricing | €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Qwen3 catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Add a public request describing your workload, context needs and preferred rental term. A request does not reserve hardware or promise a deployment. |
|---|---|
| 2 | If AxForge can offer a deployment, agree the configuration, hardware rental, licence and managed-service price in writing before anything is billed. |
| 3 | Only after availability and terms are confirmed would AxForge provision the agreed dedicated system and model build. |
| 4 | After provisioning, point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | After provisioning, adjust the term (hour, week, month or year) as your workload settles. |
Request model or sign in to start.
FAQ
This page describes the managed deployment option. Availability, the model build, hardware, licence and price must be agreed before a deployment can be offered. A public request does not provision or reserve a machine. Check the console for the current serverless offering list.
8B and 14B for fast general use on a dedicated DGX Spark, 32B or 30B-A3B when quality matters; the 235B MoE is a multi-GPU deployment.
Qwen3.8 27B is the newer generation; check the console for its current serverless availability. Qwen3 is the broader family with more sizes, the choice when you want a specific size on your own machine.
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.
For a deployment agreed after availability is confirmed: Hardware by the hour, week, month or year; the managed service is quoted per deployment. Both are confirmed in writing before anything is billed.