Liquid AI says its LFM2.5-24B-A2B model supports llama.cpp and GGUF, MLX for Apple Silicon, vLLM, SGLang, and ONNX on day one. The company reports 184 tokens/s decoding on an Apple M5 Max. Users can download the weights and fine-tune and deploy the model on their own hardware.
Part of a thread · earlier post
The model is designed for inference efficiency anywhere, with full day-one support for:
llama.cpp and GGUF
MLX for Apple Silicon
vLLM (@vllm_project) and SGLang (@sgl_project) 🤝
ONNX
For example, 𝙻𝙵𝙼𝟸.𝟻-𝟸𝟺𝙱-𝙰𝟸𝙱 decodes 184 tokens/s on Apple M5 Max. You can download the weights, fine-tune, and deploy on your own hardware.
2/
Source: Liquid AI · x.comPublished · added here
