Dedicated model · Available as managed deployment
Qwen's coding model for agents: an 80B mixture-of-experts with 3B active parameters and a 262,144-token context, released as FP8 under Apache-2.0. Available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only, as an OpenAI-compatible endpoint on hardware only you use, hosted in the EU.
Why Qwen3-Coder-Next
| Built for coding agents | Trained for tool use, multi-file edits and long agent runs rather than single completions. It is the model behind IDE agents and CI assistants. |
|---|---|
| 80B quality, 3B speed | A mixture-of-experts activates about 3B parameters per token, so it answers with the latency of a small model and the knowledge of a large one. |
| A whole repository in context | 262,144 tokens is enough to hold a codebase, its tests and the conversation, all on your own machine, with nothing leaving the EU. |
Specifications
| Model | Qwen3-Coder-Next by Qwen |
|---|---|
| Modalities | Text |
| Sizes | 79.7B |
| Context window | 262,144 tokens |
| Released | 2026-02 |
| Popularity | 1.8M downloads / month on HuggingFace |
| Licence | Open weights (Apache 2.0); commercial use permitted |
| Availability | Available as managed deployment, operated by AxForge on hardware reserved for you |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory) in a quantized build, owned and operated by AxForge |
| Region | Málaga, Spain (eu-es-1) |
| Pricing | Hardware from €0.85/hour, rental term: Hour, week, month or year. Managed service quoted per deployment. Request deployment and we confirm both in writing. |
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the model card in the catalogue and the official card on HuggingFace.
Deployment
| System | A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory), reserved for you |
|---|---|
| Commercial model | Hour, week, month or year. Hardware from €0.85/hour, managed service quoted per deployment |
| Endpoint | OpenAI-compatible /v1 on your own machine, only your traffic |
| Location | Hosted in the EU: Málaga, Spain (eu-es-1) |
| Data handling | Zero prompt retention, same policy as the serverless API |
The model is validated on AxForge hardware and deployed on your system. After deployment, your endpoint speaks the OpenAI API with the model name you receive with the deployment.
Data & privacy
Prompts and completions are processed in memory in the EU, not written to disk, not logged, not retained, and never used to train anything. We keep only request metadata (token counts, timestamps, status) for billing and operations. The full policy is at axforge.ai/privacy.
FAQ
Not on the serverless API. It is available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
The FP8 release is sized for a single large-memory machine; AxForge validates the build on the Spark and scopes a multi-GPU system if your traffic needs it.
Anything that speaks the OpenAI API (Cline, Continue, Aider, Codex-style agents and the OpenAI SDKs) pointed at your own endpoint.
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the official model card.
A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) rented by the hour, week, month or year, running Qwen3-Coder-Next behind an OpenAI-compatible endpoint on your own machine, hosted in the EU with zero prompt retention.
Hardware from €0.85/hour, by the hour, week, month or year; the managed service is quoted per deployment. Request deployment and we confirm both in writing.
Explore