Dedicated model · Available as managed deployment
Qwen's speech-recognition models — 0.6B and 1.7B — with language identification and transcription for 52 languages and dialects, 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.
Why AxForge
| 52 languages, one model | Language identification plus transcription in one pass — no per-language deployment. |
|---|---|
| Small and fast | 0.6B and 1.7B parameters: hours of audio per hour on a single dedicated machine. |
| Apache-2.0 | Permissive weights — commercial use, no licence conversation; your audio never leaves the EU. |
Specifications
| Model | Qwen3-ASR — Qwen |
|---|---|
| Modalities | Speech → text |
| Sizes | 782M, 938M, 2.0B, 2.3B |
| 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 | €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 service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Full details, benchmarks and FAQ on the Qwen3-ASR page. Prices exclude VAT.
How it works
| 1 | Request deployment — describe your traffic, context needs and rental term. |
|---|---|
| 2 | You receive the configuration, hardware rental and managed-service price in writing before anything is billed. |
| 3 | AxForge deploys Qwen3-ASR on a dedicated DGX Spark reserved for you. |
| 4 | Point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | Adjust the term — hour, week, month or year — as your workload settles. |
Request deployment or sign in to start.
FAQ
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.
Whisper is what AxForge serves per minute; Qwen3-ASR is the newer option for a dedicated deployment, with built-in language identification and a smaller footprint.
The models are built for batch and streaming transcription; AxForge confirms the streaming setup with the deployment.
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.
Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.