1 post

Posts tagged CUDA

All tags

1. 08/30/2026

   The MacBook Pro M4 has more RAM than the 5090 and I stay with CUDA

   The 48 GB unified memory in the M4 holds more than the 5090's 32 GB. Nevertheless, vLLM, llama.cpp, and diffusion remain on NVIDIA because decoding is bandwidth and the stack I already use is CUDA.

   • #local-llm
   • #apple-silicon
   • #rtx-5090
   • #cuda
   • #vllm
   • #llama-cpp