{"v":1,"id":"model:hf:LiquidAI/LFM2.5-8B-A1B-GGUF","slug":"model-liquidai-lfm2-5-8b-a1b-gguf","kind":"model","category":"llm","title":"LFM2.5-8B-A1B-GGUF","summary":"LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.","source":{"provider":"hf","ref":"LiquidAI/LFM2.5-8B-A1B-GGUF","url":"https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF","rev":"49c14831707011e64d70b2ebd8462ba08d608434","fetchedAt":"2026-10-02T21:00:15.383Z","etag":"W/\"2047-vJ+fy7ziJBr/V7MZYuBaiTchriA\""},"author":{"name":"LiquidAI","url":"https://huggingface.co/LiquidAI"},"license":{"spdx":null,"raw":"other","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":507168,"downloadsWeek":327838,"likes":309,"takenAt":"2026-10-02T21:00:15.383Z"},"tags":["gguf","liquid","lfm2","edge","llama.cpp","text-generation","en","ar","zh","fr","de","ja","ko","es","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-08-24T19:41:51.000Z","collectedAt":"2026-10-02T21:00:15.383Z","review":{"numbers":["507,168 downloads on Hugging Face","309 likes","license other","4.8 GB for LFM2.5-8B-A1B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:00:15.383Z","http":200},"description":"Try LFM •\n    Docs •\n    LEAP •\n    Discord\n\n# LFM2.5-8B-A1B-GGUF\n\nLFM2 is a new generation of hybrid models developed by [Liquid AI](https://www.liquid.ai/), specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.\n\nFind more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B\n\n## 🏃 How to run LFM2\n\nExample usage with [llama.cpp](https://github.com/ggml-org/llama.cpp):\n\n```\nllama-cli -hf LiquidAI/LFM2.5-8B-A1B-GGUF --conversation \\\n    --temp 0.2 --top-k 80 --repeat-penalty 1.05\n```\n\nSource: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF","install":{"kind":"model","hfId":"LiquidAI/LFM2.5-8B-A1B-GGUF","gated":false,"format":"gguf","files":[{"name":"LFM2.5-8B-A1B-BF16.gguf","size":16947260640,"quant":"BF16","sha256":"2b471037695ef5908cb88065c7ebb23fe285a07950d7433fabf0c865273728ab"},{"name":"LFM2.5-8B-A1B-F16.gguf","size":16947260640,"quant":"F16","sha256":"c6eb857414327e26d32654d996838d305cb57c01c06def0894bde244f7baa159"},{"name":"LFM2.5-8B-A1B-Q4_0.gguf","size":4844678368,"quant":"Q4_0","sha256":"48ed1465d761311b2fd57b7fb46cf969a20b3a8281945b04e10f52bd1609e715"},{"name":"LFM2.5-8B-A1B-Q4_K_M.gguf","size":5155564768,"quant":"Q4_K_M","sha256":"4923ec14f06b968b74d663e5949867d2d9c3bf13a20b8be1a9f9af39989b2bb0"},{"name":"LFM2.5-8B-A1B-Q5_K_M.gguf","size":6030339296,"quant":"Q5_K_M","sha256":"eb8bd10148ea21e195502d6d6a205983ba40815302068ce72eb160684df92b3e"},{"name":"LFM2.5-8B-A1B-Q6_K.gguf","size":6959787232,"quant":"Q6_K","sha256":"7ccf57a2d410d8822d1560a1ca10c8318f3e15d6a8f6d42d1903d58e80ea20a6"},{"name":"LFM2.5-8B-A1B-Q8_0.gguf","size":9010195680,"quant":"Q8_0","sha256":"33ab3b8ce6a964fb8ebac89360c9b3cf72c4fa418d5e4c0a94d46883124d5c02"}],"totalBytes":65895086624,"suggestedFile":"LFM2.5-8B-A1B-Q4_K_M.gguf","requirements":{"ramGb":7,"diskBytes":5155564768,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:LiquidAI/LFM2.5-8B-A1B-GGUF"}}