Apple ran Meta's 816B Muse Spark Open on four Mac Studios at over 36 tokens a second
Apple ran Meta's Muse Spark Open, an 816-billion-parameter model with 42 billion parameters active at a time, across four Mac Studios and measured more than 36 tokens per second. Apple's machine learning researchers said the model "cannot fit on a single machine", with figures based on four M5 Ultra machines splitting it by width; the context is truncated.
AI summary · generated only from source feed metadata; consult originalSource published
Published here
views7
Original source
MIXED — XR
Media report · consult original reporting
Read the original ↗https://mixed-news.com/en/apple-mlx-muse-spark-open-four-mac-studios-36-tokens/Original headline
Apple ran Meta's 816B Muse Spark Open on four Mac Studios at over 36 tokens a second
AI bilingual edit · consult originalHeadlines are indexed or machine translated, not independent verification of scientific results. Medical news is not clinical advice. Distinguish interstellar concepts from demonstrated space technology using the original source.