New models
Newly released open models, run on your own machines: the hardware they need, how fast they go, and how to use them from your coding agent.
New models
Run Ripple-65B locally: memory, speed and the benchmark gap
Ripple-65B Preview on your own hardware: real download sizes, the first DGX Spark speed figure, llama.cpp and Ollama support, and its disputed scores.
New models
Best local LLM by memory: what fits in 16GB to 512GB
The strongest open model that fits at 16, 24, 32, 64, 128, 256 and 512GB of VRAM or unified memory, with real download sizes and sourced speeds.