Guides 3
Short guides for choosing hardware to run open models, each linked to the devices and models it covers.
- How to choose a GPU for local LLMsPick a GPU for local LLMs by memory first, bandwidth second and software support third. Consumer cards, the RTX PRO 6000, Macs and the DGX Spark.
- RTX PRO 6000 Blackwell for local AIThe RTX PRO 6000 Blackwell has 96 GB of GDDR7. Specs for each edition, what that memory makes possible, and how it compares with the RTX 5090.
- Which open models run on the NVIDIA DGX SparkThe DGX Spark has 128 GB of unified memory. See how that decides which open models fit, how clustering works, and when renting is the better choice.
Keep exploring
- WatchNew labs and architectures, with vendor claims checked against sources.
- LicensesWhat each model license allows, in plain English.
- China DeskWho owns the Chinese labs and what their models are.
- Run open modelsCommands to run open models with Ollama, MLX and GGUF.
- CUDA and alternativesCUDA, ROCm, Metal and the other stacks that run models.
- Model typesText, coding, image, video, audio, embedding and vision models.