llama serve -hf ggml-org/Muse-Spark-Open-816B-A42B-GGUF:Q2_K
this model also goes so well with @pidotdev agent to get stuff done! 🤯
Muse Spark Open 816B runs locally via llama.cpp on a Mac
AISummary
Hugging Face's Merve Noyan shares a llama.cpp command serving the Muse-Spark-Open-816B-A42B GGUF Q2_K quantization, and says it pairs well with the pi.dev agent. Pedro Cuenca says the model runs on a Mac M3 Ultra with 512GB of memory, which he calls a frontier model on a desktop.
Post on XView on X
merveVerified on X
@mervenoyann
And of course Muse Spark Open works great with llama.cpp 🦙🔥 Behold this amazing demo courtesy of @mervenoyann, running on a Mac (M3 Ultra 512). This is a frontier model that runs on your (beefy) desktop. Local AI is only getting better 🚀
Source: merve · x.comPublished · added here