1× RTX A400016 GB VRAM
Nosana network, hosts worldwide
Details
Stock and price checked 17 min ago.
Self-service: you start it yourself, with no order or sales contact.
nvidia-a4000
Full price
€0.11
per hour, whole instance, 1 GPU
ccore
Qwen3.5-4B-GLB-3D-Coder
text generationapache-2.038.7K downloadsHugging Face
Cheapest GPU in stock that fits
A single GPU with at least 10 GB for inference.
View offer
GPU memory it needs (estimate)
Rule of thumb from the model's size. Real needs depend on batch size, context length and framework.
Inference (full precision)
10 GB
Inference (8-bit)
5.1 GB
Inference (4-bit)
2.5 GB
LoRA fine-tuning
11 GB
QLoRA (8-bit base)
5.5 GB
Full fine-tuning
41 GB