liquid.ai · Open Weight Models
Liquid AI's LFM3 family of small open weight models: a 1.7B text model with 256K context plus 2B vision, audio, omni and d1 decision versions, with official GGUF, MLX and ONNX builds.
LFM3 (Liquid AI) is one of 21 open weight model tools on Axiomi. See all open weight model tools or how we check facts.
// guides
How to run LFM3 locally with Ollama, llama.cpp or LM Studio: Liquid AI's 1.7B model, memory by quant, the VL, Audio and Omni versions, and the license limits.
// related
LFM2 / LFM2.5 (Liquid AI)liquid.aiLiquid AI's LFM2 and LFM2.5 open weight edge models, including LFM2.5-24B-A2B (24B MoE, ~2.45B active, 131K context) with official GGUF, MLX, vLLM and SGLang builds.Open Weight ModelsSee siteHN 19
Bonsai (Prism ML)prismml.comPrism ML's family of 1 bit and ternary open weight models, including Bonsai 2 27B, a Qwen3.8-27B derivative that fits in about 6 to 7 GB and runs on Prism's llama.cpp fork.Open Weight ModelsOpen source★ 3.5k
Muse Spark Open (Meta)research.meta.aiMeta's open weight multimodal MoE model (816B total, ~42B active, 1M context) for coding and agents, with BF16 and NVFP4 weights plus community GGUF and MLX builds.Open Weight ModelsSee site
Gemmadeepmind.googleGoogle DeepMind's lightweight open models built from Gemini research, sized to run on laptops, phones and single GPUs.Open Weight ModelsOpen source★ 5.8k
Llamallama.comMeta's family of open weight language models, released with weights for research and commercial use under the Llama community licence.Open Weight ModelsOpen source★ 7.7k
Recursive Flintrecursive.comRecursive's Apache 2.0 open weight coding model: a mixture of experts with 39.8B total and about 2.5B active parameters, a 262K context and tool calls.Open Weight ModelsOpen source