Dedicated model · Available as managed deployment
Meta's Llama 3.1 family of 8B, 70B and 405B instruction-tuned models with a 128k-token context and multilingual training, the most deployed open LLM family in production. 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 Llama 3.1
| The default open model | Llama 3.1 is what most teams standardise on: mature tooling, broad framework support and years of community fine-tunes and evaluations. |
|---|---|
| 8B and 70B on one machine | The 8B runs comfortably on a dedicated DGX Spark; the 70B fits the same machine in a quantized build. 405B is a multi-GPU deployment. |
| Licence handled | The Llama 3.1 community licence allows commercial use under its conditions; AxForge deploys under it and tells you exactly what applies to you. |
Specifications
| Model | Llama 3.1 by meta-llama |
|---|---|
| Modalities | Text |
| Sizes | 8.0B, 70.6B, 405.9B |
| Released | 2024-07 |
| Popularity | 5.9M downloads / month on HuggingFace |
| Licence | Open, with conditions (llama3.1); AxForge deploys under it and tells you what applies |
| Availability | Available as managed deployment, operated by AxForge on hardware reserved for you |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), 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.
8B natively and 70B in a quantized build, both with the 128k context; 405B needs a multi-GPU system, which AxForge scopes with you.
Under the Llama 3.1 community licence, yes for almost every business. The licence carries conditions, and AxForge walks you through them before deployment.
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 Llama 3.1 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