Tag
LiquidAI releases draft models for speculative decoding to accelerate their LFM2.5 models, achieving up to 2× faster inference on H100 and Apple silicon without quality degradation.
LiquidAI releases LFM 2.5, a language model optimized for quantized deployment, with GGUF format available on Hugging Face.
LiquidAI releases LFM2.5-VL-3B, a 3B multimodal model for on-device deployment with improved OCR, grounding, and efficient inference, available in multiple formats including GGUF, ONNX, and MLX.