{"type":"post","id":"llama-cpp-v0-8-0-adds-liquidai-lfm3-a547b8","slug":"llama-cpp-v0-8-0-adds-liquidai-lfm3-a547b8","title":"llama.cpp v0.8.0 adds LiquidAI LFM3 family including LFM3-Audio-2B, with streaming audio and new /v1/realtime and /tts server endpoints","description":"llama.cpp v0.8.0 adds support for LiquidAI's LFM3 text, vision, audio and omni models, alongside experimental streaming-audio handling and server endpoints for realtime conversation and text-to-speech.","retrieval_nugget":"llama.cpp v0.8.0 adds support for LiquidAI's LFM3 text, vision, audio and omni models, alongside experimental streaming-audio handling and server endpoints for realtime conversation and text-to-speech. For teams building local voice applications, the release supplies a new serving path; it does not establish performance, hardware requirements or production readiness.","published_at":"2026-10-31","updated_at":"2026-10-31","record_date":"2026-10-31","date_kind":"published_at","topics":["generative-media","multimodal"],"entities":["llama.cpp","Liquid AI","LFM3-Audio-2B","LFM3-Omni-2B","LFM3-1.7B","LFM3-VL-2B"],"related_patterns":["generative-media-becomes-application-infrastructure"],"novelty_label":"new_fact","what_changed":"llama.cpp v0.8.0 adds LFM3-family support and experimental streaming audio, connecting it to realtime server and /tts endpoints.","prior_refs":["memory:670a4da9-1d6b-87a6-a765-8b400f8dbe2b","memory:26971ad6-2df8-8112-ace6-cf974dab4720"],"source_url":"https://github.com/ggml-org/llama.cpp/releases/tag/v0.8.0","source_urls":["https://github.com/ggml-org/llama.cpp/releases/tag/v0.8.0"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:llama-cpp-v0-8-0-adds-liquidai-lfm3-a547b8","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/llama-cpp-v0-8-0-adds-liquidai-lfm3-a547b8/","markdown":"https://newruntime.com/posts/llama-cpp-v0-8-0-adds-liquidai-lfm3-a547b8.md","json":"https://newruntime.com/posts/llama-cpp-v0-8-0-adds-liquidai-lfm3-a547b8.json"},"next_reads":[{"type":"topic","path":"/topics/generative-media/","url":"https://newruntime.com/topics/generative-media/","title":"Generative Media","reason":"Explore the generative-media topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/generative-media.md","json_url":"https://newruntime.com/topics/generative-media.json"},{"type":"topic","path":"/topics/multimodal/","url":"https://newruntime.com/topics/multimodal/","title":"Multimodal","reason":"Explore the multimodal topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/multimodal.md","json_url":"https://newruntime.com/topics/multimodal.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"}]}