- Version Inference-2024.12.23-LLAMA.CPP-Ubu22
- Sold by NI SP - High-End Remote Desktop and HPC
Starting from $0.06 to $0.56/hr for software + AWS usage fees
Run AI Inference on your own server for coding support, creative writing, summarizing, ... without sharing data with other services. The Inference server has all you need to run state-of-the-art inference on GPU servers. Includes llama.cpp inference, latest CUDA and NVIDIA Docker container support. Support for llama-cpp-python, Open Interpreter, Tabby coding assistant.