{"schema":"postcutoff/model@1","as_of":"2026-10-15T10:09:00+02:00","url":"https://postcutoff.com/m/liquid-lfm2-5-24b-a2b/","md":"https://postcutoff.com/m/liquid-lfm2-5-24b-a2b/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"liquid-lfm2-5-24b-a2b","name":"LFM2.5-24B-A2B","org":"Liquid AI","family":"LFM2.5","released":"2026-10-13","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"lfm1.0","context_window":131072,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0.1,"output":1,"unit":"per 1M tokens","source":"https://www.liquid.ai/blog/lfm2-5-24b-a2b"},"price_line":"$0.10 in, $1 out per 1M tokens","access":[{"provider":"Hugging Face","url":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"provider":"Liquid AI Console","url":"https://console.liquid.ai"},{"provider":"Liquid Playground","url":"https://playground.liquid.ai"}],"capabilities":[{"name":"On-device agent MoE","detail":"24B total / 2B active parameters; 184 tokens/s on an Apple M5 Max and vendor-reported AutomationBench 27.69 vs 8.72 for Qwen3.6-35B-A3B.","first":false,"discovered":"launch","source":"https://www.liquid.ai/blog/lfm2-5-24b-a2b"}],"entry":"2026-10-13-liquid-ai-lfm2-5-24b-a2b","notes":"Reasoning-only; cached input $0.05 per 1M. Weaker than Qwen3.6-35B-A3B on GPQA Diamond and SWE-bench Verified (vendor numbers). Console model id not verified.","verified":"2026-10-15","body_md":"Open-weight sparse model from Liquid AI for local agents; day-one llama.cpp (GGUF), MLX, vLLM, SGLang and ONNX support.","page_url":"https://postcutoff.com/m/liquid-lfm2-5-24b-a2b/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":37,"you_url":"https://postcutoff.com/you/liquid-lfm2-5-24b-a2b/","briefings":null}