{"type":"post","id":"gb300-nvl72-vs-mi355x-muse-spark-open-cd7374","slug":"gb300-nvl72-vs-mi355x-muse-spark-open-cd7374","title":"GB300 NVL72 vs MI355X: Muse Spark Open","description":"SemiAnalysis’s InferenceX page compares Meta’s Muse Spark Open 816B running in FP4 on NVIDIA GB300 NVL72 and AMD MI355X.","retrieval_nugget":"SemiAnalysis’s InferenceX page compares Meta’s Muse Spark Open 816B running in FP4 on NVIDIA GB300 NVL72 and AMD MI355X. Across three agentic-workload operating points, GB300 delivers substantially higher chip throughput, while the lower-cost option changes with the target interactivity—an important reminder to benchmark at the service level a team actually needs.","published_at":"2026-11-03","updated_at":"2026-11-03","record_date":"2026-11-03","date_kind":"published_at","topics":["agent-economics"],"entities":["SemiAnalysis","InferenceX","Muse Spark Open","NVIDIA GB300 NVL72","AMD MI355X","AgentX"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"Adds a head-to-head Muse Spark Open benchmark of GB300 NVL72 versus AMD MI355X, including throughput and cost comparisons at multiple interactivity targets.","prior_refs":[],"source_url":"https://inferencex.semianalysis.com/compare/muse-spark-open-gb300-vs-mi355x","source_urls":["https://inferencex.semianalysis.com/compare/muse-spark-open-gb300-vs-mi355x"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:gb300-nvl72-vs-mi355x-muse-spark-open-cd7374","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/gb300-nvl72-vs-mi355x-muse-spark-open-cd7374/","markdown":"https://newruntime.com/posts/gb300-nvl72-vs-mi355x-muse-spark-open-cd7374.md","json":"https://newruntime.com/posts/gb300-nvl72-vs-mi355x-muse-spark-open-cd7374.json"},"markdown_url":"https://newruntime.com/posts/gb300-nvl72-vs-mi355x-muse-spark-open-cd7374.md","next_reads":[{"type":"topic","path":"/topics/agent-economics/","url":"https://newruntime.com/topics/agent-economics/","title":"Agent Economics","reason":"Explore the agent-economics topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-economics.md","json_url":"https://newruntime.com/topics/agent-economics.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}