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. We're releasing the weights of four post-trained checkpoints with 350M, 700M, 1.2B, and 2.6B parameters. They provide the following key features to create AI-powered edge applications: * **Fast training & inference** – LFM2 achieves 3x faster training compared to its previous generation. It also benefits from 2x faster decode and prefill speed on CPU compared to Qwen3. * **Best performance** – LFM2 outperforms similarly-sized models across multiple benchmark categories, including knowledge, mathematics, instruction following, and multilingual capabilities. * **New architecture** – LFM2 is a new hybrid Liquid model with multiplicative gates and short convolutions. * **Flexible deployment** – LFM2 runs efficiently on CPU, GPU, and NPU hardware for flexible deployment on smartphones, laptops, or vehicles.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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. We're releasing the weights of four post-trained checkpoints with 350M, 700M, 1.2B, and 2.6B parameters. They provide the following key features to create AI-powered edge applications: Due to their small size, **we recommend fine-tuning LFM2 models on narrow use cases** to maximize performance. They are particularly suited for agentic tasks, data extraction, RAG, creative writing, and multi-turn conversations. However, we do not recommend using them for tasks that are knowledge-intensive or require programming skills.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. - **Best-in-class performance**: A 1.2B model rivaling much larger models, bringing high-quality AI to your pocket. - **Fast edge inference**: 239 tok/s decode on AMD CPU, 82 tok/s on mobile NPU. Runs under 1GB of memory with day-one support for llama.cpp, MLX, and vLLM. - **Scaled training**: Extended pre-training from 10T to 28T tokens and large-scale multi-stage reinforcement learning. Find more information about LFM2.5 in our blog post.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. We recommend using it for agentic tasks, data extraction, and RAG. It is not recommended for knowledge-intensive tasks and programming. 1. **Function definition**: We recommend providing the list of tools as a JSON object in the system prompt. You can also use the `tokenizer.apply_chat_template()` function with tools. 2. **Function call**: By default, LFM2.5 writes Pythonic function calls (a Python list between ` ` and ` ` special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt. 3. **Function execution**: The function call is executed, and the result is returned as a "tool" role. 4. **Final answer**: LFM2 interprets the outcome of the function call to address the original user prompt in plain text.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LFM2.5-2.6B is part of LFM2.5, a family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with a 128K context window and agentic post-training. - **Best-in-class agent**: Competitive with models 4x larger on tool use, instruction following, and multi-step agentic tasks. - **Agentic reinforcement learning**: Trained inside the most popular agentic harnesses to improve compatibility. - **Efficient inference**: 220 tok/s on an Apple M5 Max and 113 tok/s on an AMD Ryzen CPU, in under 2.5 GB of memory. Find more information about LFM2.5-2.6B in our blog post.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. - **On-device personal assistant**: Designed to power real-life applications, chaining tool calls, and following complex instructions on all devices. - **Compressed performance**: Competitive with much larger dense and MoE models on instruction following and agentic tasks. - **Unmatched throughput**: Fastest in its size class on both CPU and GPU inference, with day-one support for llama.cpp, MLX, vLLM, and SGLang. Find more information about LFM2.5-8B-A1B in our blog post.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LFM2.5‑VL-1.6B is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-1.6B, built on an updated backbone LFM2.5-1.2B-Base and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post. * **Enhanced instruction following** on vision and language tasks. * **Improved multilingual vision understanding** in Arabic, Chinese, French, German, Japanese, Korean, and Spanish. * **Robust understanding of visual content** with improved results on multi-image inputs, high-resolution images, and OCR. 🎥⚡️ You can try LFM2.5-VL-1.6B running locally in your browser with our real-time video stream captioning WebGPU demo 🎥⚡️
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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. We're releasing the weights of our first MoE based on LFM2, with 8.3B total parameters and 1.5B active parameters. Due to their small size, **we recommend fine-tuning LFM2 models on narrow use cases** to maximize performance. They are particularly suited for agentic tasks, data extraction, RAG, creative writing, and multi-turn conversations. However, we do not recommend using them for tasks that are knowledge-intensive or require programming skills.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗d1-3B is a 3B parameter **decision model** built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in **one forward pass with zero output tokens**. - **Best decision model under 10B on the Decision Index 0.2.1**: 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). - **Multimodal**: images and text in the same state. It scores 74.1 on 11 public image benchmarks (LFM2.5-VL-3B: 73.9). - **Fast**: 8 ms a decision on an NVIDIA RTX 4090, 9 ms on an AMD MI325X, 30 ms on an Apple M5 Pro. Find more information about open d1 in our blog post.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗d1-3B is a decision model developed by Liquid AI: it answers named, typed questions over a state (text, JSON or images) in one forward pass, with no generated tokens. Find more details in the original model card: https://huggingface.co/LiquidAI/d1-3B
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Audio · Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens. llama.cpp answers `noul`, `choice` and `score` questions over a state (text or JSON), pictures, a video, audio clips, and questions written or spoken. Videos are read as their frames, and video input needs `ffmpeg` in `PATH`. Multiple choice (`"multiple": true`), extraction, estimates and boxes are not supported yet. A question is read in one batch, so `-b` and `-ub` must hold its state and media. A picture takes at most half of `-ub`: 8192 keeps the full budget of 4096 tokens per picture, smaller values lower it.
Input Audio · Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗d1-omni-600M is a 600M parameter **decision model** built on LFM2.5-Encoder-350M. You give it a state (text or JSON, with images or a voice clip) and a set of named questions. It returns typed answers with **zero output tokens**: every answer is read directly from the model's distribution over the options, with no generation and no parsing. - **Vision-language**: text and images (tiled for large frames, several images per state) in a single forward pass. - **Audio-language**: text and up to 30 s of speech in a single forward pass. - **Edge-sized**: 587M parameters: a 381M shared trunk and decision head, a 94M vision encoder and a 112M audio encoder. Every modality runs the same trunk weights. Find more information about open d1 in our blog post.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗d1-omni-600M is a decision model developed by Liquid AI: it answers named, typed questions over a state (text, JSON, images or audio) in one forward pass, with no generated tokens. A question is read in one batch, so `-b` and `-ub` must hold it: 4096 covers any image and states of a few thousand tokens, raise them up to 16384 for longer states. The state can be `null` when the images or the audio are the whole state. A request carries images or one audio clip (up to 30 s), not both.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗