{"type":"post","id":"kapitsa-0-2-24-starts-a-splash-engine-7843ad","slug":"kapitsa-0-2-24-starts-a-splash-engine-7843ad","title":"Kapitsa 0.2.24 starts a Splash engine backend and lets Qwen3.5 MLX packs use their own MTP head for drafting","description":"Kapitsa 0.2.24 adds a Splash engine backend to its serving path and enables Qwen3.5 MLX packs with their own MTP head to draft tokens rather than decode plainly.","retrieval_nugget":"Kapitsa 0.2.24 adds a Splash engine backend to its serving path and enables Qwen3.5 MLX packs with their own MTP head to draft tokens rather than decode plainly. The release reports 37.1 tokens per second for a 27B pack on an M5 Pro, up from 16.1 with the same greedy text.","published_at":"2026-10-31","updated_at":"2026-10-31","record_date":"2026-10-31","date_kind":"published_at","topics":["harness-engineering","agent-runtime"],"entities":["Kapitsa","Splash","Qwen3.5","nace-ai","Jundot"],"related_patterns":["harness-architecture-outlives-model-choice"],"novelty_label":"new_fact","what_changed":"Kapitsa 0.2.24 adds a Splash engine backend and lets Qwen3.5 MLX packs use their own MTP head for drafting.","prior_refs":["memory:1b761bdf-24c1-84a0-acbe-1882ef2b1d83","memory:0eb3ca5c-6706-8780-a1c3-e6dd7e517504"],"source_url":"https://github.com/nace-ai/kapitsa/releases/tag/v0.2.24","source_urls":["https://github.com/nace-ai/kapitsa/releases/tag/v0.2.24"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:kapitsa-0-2-24-starts-a-splash-engine-7843ad","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/kapitsa-0-2-24-starts-a-splash-engine-7843ad/","markdown":"https://newruntime.com/posts/kapitsa-0-2-24-starts-a-splash-engine-7843ad.md","json":"https://newruntime.com/posts/kapitsa-0-2-24-starts-a-splash-engine-7843ad.json"},"next_reads":[{"type":"topic","path":"/topics/harness-engineering/","url":"https://newruntime.com/topics/harness-engineering/","title":"Harness Engineering","reason":"Explore the harness-engineering topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/harness-engineering.md","json_url":"https://newruntime.com/topics/harness-engineering.json"},{"type":"topic","path":"/topics/agent-runtime/","url":"https://newruntime.com/topics/agent-runtime/","title":"Agent Runtime","reason":"Explore the agent-runtime topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-runtime.md","json_url":"https://newruntime.com/topics/agent-runtime.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":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}