7361. Copy link NVIDIA DGX Spark + Apple Mac Studio = 4x Faster LLM Inference with EXO 1.0 simonwillison.net/2025/Oct/16/nvidia-dgx-spark-apple-mac-studio#atom-everything ai,apple,generative-ai,llms,local-llms,nvidia
7343. Copy link llama.cpp guide: running gpt-oss with llama.cpp simonwillison.net/2025/Aug/19/gpt-oss-with-llama-cpp#atom-everything ai,generative-ai,gpt-oss,llama-cpp,llms,local-llms,macos,openai
7340. Copy link Introducing Gemma 3 270M: The compact model for hyper-efficient AI simonwillison.net/2025/Aug/14/gemma-3-270m#atom-everything ai,gemini,gemma,generative-ai,google,llm,llm-release,llms,lm-studio,local-llms,pelican-riding-a-bicycle