LiquidAI/LFM2.5-Encoder 250M/350M

LFM2.5-Encoder-350M is a multilingual bidirectional encoder built on the LFM2 architecture — a larger encoder for maximum downstream quality. It is a masked language model with full bidirectional attention, designed to be fine-tuned into task-specific models (classification, token classification, retrieval, reranking, and semantic similarity) across 15 languages, and to run efficiently on-device.

• Highly capable for its size. On par with the best similarly sized encoders and well ahead of our own retrieval siblings.
• General-purpose. 8k context, strong across NLI, paraphrase, sentiment, and multilingual tasks.
• Fast and on-device. Matches or beats ModernBERT throughput, with a long-context edge on CPU; runs in the browser on WebGPU.

https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M-GGUF

https://huggingface.co/LiquidAI/LFM2.5-Encoder-230M-GGUF

https://github.com/ggml-org/llama.cpp/pull/29862

example (from the hf):

❯ uv run fill-mask.py LFM2.5-Encoder-350M-F16.gguf "The capital of France is [MASK]." top-5 at [MASK]: # 1 11.42 ' Paris' # 2 10.43 'Paris' # 3 9.65 ' Nice' # 4 8.94 ' Strasbourg' # 5 8.62 ' Lyon'