alt Hacker News158GB number is for Mistral Medium 3.5 128B model, Muse Spark is way larger.
Muse Spark Open would require more than 1.6TB of RAM in its native precision (BF16) for the model parameters alone. In a 4-bit quantized (NVFP4) format, the model memory footprint is lowered to about 493GB.
So about 24gb/expert at NVFP4. If you compressed the KV cache, you might be able to get away with 2x 24GB cards and stream the experts.