{"type":"post","id":"inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5","slug":"inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5","title":"InferenceX measures Muse Spark Open on GB300 NVL72 at 43,643 tok/s per GPU and $0.015/M tokens","description":"SemiAnalysis InferenceX ranks GPUs serving Meta’s Muse Spark Open on an agentic coding workload, measuring throughput at the same per-user interaction target.","retrieval_nugget":"SemiAnalysis InferenceX ranks GPUs serving Meta’s Muse Spark Open on an agentic coding workload, measuring throughput at the same per-user interaction target. GB300 NVL72 leads on throughput, while MI355X has the lowest listed cost per million tokens among the five ranked systems. The comparison makes workload and serving conditions central to infrastructure decisions.","published_at":"2026-11-09","updated_at":"2026-11-09","record_date":"2026-11-09","date_kind":"published_at","topics":["inference","compute","coding-agents"],"entities":["SemiAnalysis","InferenceX","Muse Spark Open","GB300 NVL72","MI355X","SGLang","AgentX"],"related_patterns":[],"novelty_label":"new_fact","source_url":"https://inferencex.semianalysis.com/rankings/fastest-gpu-for-muse-spark-open","source_urls":["https://inferencex.semianalysis.com/rankings/fastest-gpu-for-muse-spark-open"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5","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/inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5/","markdown":"https://newruntime.com/posts/inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5.md","json":"https://newruntime.com/posts/inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5.json"},"markdown_url":"https://newruntime.com/posts/inferencex-measures-muse-spark-open-on-gb300-nvl72-e05cc5.md","next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"topic","path":"/topics/compute/","url":"https://newruntime.com/topics/compute/","title":"Compute","reason":"Explore the compute topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/compute.md","json_url":"https://newruntime.com/topics/compute.json"},{"type":"topic","path":"/topics/coding-agents/","url":"https://newruntime.com/topics/coding-agents/","title":"Coding Agents","reason":"Explore the coding-agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/coding-agents.md","json_url":"https://newruntime.com/topics/coding-agents.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"}]}