AxForge Dev

I'd like to use Qwen3.8 27B on AxForge.

Qwen3.8Modelsmodel-request

Fratelli adolescenti, maschio di 16 anni e femmina di 14 anni, spinto dalla curiosità fann…

I'd like to use Gemma-4 26B on AxForge.

Gemma-4Modelsmodel-request

I'd like to use Xing4.0 on AxForge. addon kodi

Xing4.0Modelsmodel-request

I'd like to use MiniMax H3 on AxForge.

MiniMax H3Modelsmodel-request

I'd like to use Upscale 2× / 4× on AxForge.

Upscale 2× / 4×Modelsmodel-request

I'd like to use NVIDIA DGX Spark (GB10) on AxForge.

NVIDIA DGX Spark (GB10)GPUsbaremetal-request

I'd like to use NVIDIA RTX 6000 Pro (96GB) on AxForge.

NVIDIA RTX 6000 ProGPUsgpu-request

I'd like to use NVIDIA H200 on AxForge.

NVIDIA H200GPUsgpu-request

I'd like to use NVIDIA RTX 3090 (budget tier) on AxForge.

NVIDIA RTX 3090GPUsgpu-request

I'd like to use NVIDIA DGX Station (GB300) on AxForge.

NVIDIA DGX Station (GB300)GPUsgpu-request

I'd like to use LTX-2.5 on AxForge.

LTX-2.5Modelsmodel-request

Hi, I'm new here. Debian repos seem to be broken on GB10: So it's not possible to build pa…

NVIDIA DGX Spark (GB10)General

I'd like to use NVIDIA RTX 5090 on AxForge.

NVIDIA RTX 5090GPUsgpu-request

I'd like to use NVIDIA H100 on AxForge.

NVIDIA H100GPUsgpu-request

I'd like to use Qwen3 30B A3B on AxForge.

Qwen3Modelsmodel-request

I'd like to use LTX-Video on AxForge.

LTX-VideoModelsmodel-request

Which GPU is better for image generation?

NVIDIA DGX Spark (GB10)GPUs

Can I install whatever CUDA version I want on the rented machine?

Can one model use all four RTX 5090s?

NVIDIA RTX 5090GPUs

Do you have speech-to-text?

What embedding model do you have?

Qwen3 EmbeddingModels

Which GPU is better for fine-tuning?

NVIDIA DGX Spark (GB10)GPUs

Do I pay while the machine is switched off?

NVIDIA DGX Spark (GB10)GPUs

Is Qwen3.6 or Qwen3.8 better?

Qwen3.8Models

Can I expose my own public API from a rented GPU?

Do you have text-to-speech?

What should I rent for Qwen3.8 27B?

NVIDIA DGX Spark (GB10)GPUs

Can a GB10 run a 70B model?

NVIDIA DGX Spark (GB10)GPUs

What happens if all the GB10s are busy?

NVIDIA DGX Spark (GB10)GPUs

What GPU is good for AI agents?

Is AxForge actually hosted in the EU?

Is AxForge GDPR compliant?

Why does the GB10 say 128 GB memory instead of 128 GB VRAM?

Can I bring my own model instead of using the models on your API?

Do I need a GPU for RAG?

How fast do I get SSH access after I book?

NVIDIA DGX Spark (GB10)GPUs

Can I run vLLM on the GB10?

NVIDIA DGX Spark (GB10)GPUs

Which models can I call on the AxForge API right now?

Can I reserve a GPU for tomorrow instead of taking whatever is free now?

NVIDIA DGX Spark (GB10)GPUs

How many users can one GB10 serve at the same time?

NVIDIA DGX Spark (GB10)GPUs

What should I use if I need lots of concurrent API users?

What logs do you keep if you say zero retention?

How fast is Qwen3.8 on AxForge?

Qwen3.8Models

Can I use these open models commercially?

What model should I start with if I just want a good general chatbot?

Qwen3.8Models