lfm2 - Robuta Search

https://docs.vllm.ai/en/latest/api/vllm/model_executor/models/lfm2_vl/ lfm2_vl - vLLM vl vllm lfm2 https://www.liquid.ai/blog/introducing-lfm2-2-6b-redefining-efficiency-in-language-models Introducing LFM2-2.6B: Redefining Efficiency in Language Models | Liquid AI Sep 23, 2025 - We're excited to announce LFM2-2.6B, the newest and currently largest model in our Liquid Foundation Model 2 series. Building on our 350M, 700M, and 1.2B... 2 6b redefining efficiency language models liquid ai introducing https://huggingface.co/docs/transformers/model_doc/lfm2 LFM2 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. hugging face lfm2 https://www.liquid.ai/blog/lfm2-vl-efficient-vision-language-models LFM2-VL: Efficient Vision-Language Models | Liquid AI Oct 21, 2025 - Today, we release LFM2-VL, our first series of vision-language foundation models. These multimodal models are designed for low-latency and device-aware... vision language models liquid ai lfm2 vl efficient https://unsloth.ai/docs/models/tutorials/lfm2.5 Liquid LFM2.5: How To Run & Fine-tune | Unsloth Documentation Run and fine-tune LFM2.5 Instruct and Vision locally on your device! run fine tune unsloth documentation liquid lfm2 5 https://trymirai.com/local-models/liquidai-lfm2-5-1-2b-instruct LFM2.5-1.2B-Instruct from LiquidAI – Run On-Device with Mirai. Run LFM2.5-1.2B-Instruct AI model directly on iOS or Mac locally using Mirai SDK. With zero latency, full data privacy, and no inference costs. Integrate AI in... 5 1 2b instruct lfm2 run device https://ollama.com/library/lfm2 lfm2 LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion... lfm2 https://www.liquid.ai/blog/lfm2-8b-a1b-an-efficient-on-device-mixture-of-experts LFM2-8B-A1B: An Efficient On-device Mixture-of-Experts | Liquid AI Oct 24, 2025 - We are releasing LFM2-8B-A1B, our first on-device Mixture-of-Experts (MoE) with 8.3B total parameters and 1.5B active parameters per token. By activating only... liquid ai lfm2 8b efficient device