A user shared a `llama serve` command for the GGUF Q2_K version, saying the setup used two Mac Studios.
A user shared the command llama serve -hf ggml-org/Muse-Spark-Open-816B-A42B-GGUF:Q2_K and said it was used on two Mac Studios. The post also links to a video.
26.8K
2 Sources, first seen ago
Clément Delangue shared a llama-server command for the Muse-Spark-Open-816B-A42B GGUF repository and said the setup ran on two Mac Studios.
llama serve -hf ggml-org/Muse-Spark-Open-816B-A42B-GGUF:Q2_K
The post identifies the Q2_K repository variant and includes a native X video. The official Hugging Face account reposted Delangue's message but added no technical details.
Delangue's text does not identify the Mac Studio generation, chip or memory configuration, explain how the two machines were connected, or provide latency, throughput or output-quality measurements. It documents the command and Delangue's two-machine claim but provides no basis for comparing this setup with other hardware.
—
Not ranked yet
—
Not ranked yet
