I now have identical professional AI/ML development environments on both my HP Laptop and ASUS Desktop running Debian 13 (Trixie).
Installed on both machines:
🐍 Python Environment (ai-env via Miniforge)
- PyTorch (CPU) + torchvision + torchaudio
- Transformers, Diffusers, TRL, PEFT, LangChain, Gradio
- Full Hugging Face stack, sentence-transformers, bitsandbytes, etc.
R + RStudio
- Latest tidyverse
- ML packages: xgboost, lightgbm, caret, randomForest, ranger, glmnet
- reticulate (seamless R ↔ Python integration)
Additional Tools
- JupyterLab
- Quarto (for beautiful reports and dashboards)
- All necessary system dependencies
Key Achievement: R can now successfully call PyTorch and other Python libraries from RStudio using reticulate.
Both machines are now ready for:
- Local LLMs & fine-tuning
- Image generation with Diffusers
- Data analysis in R or Python
- Building Gradio web apps
- Mixed R + Python workflows