LiquidAI has released LFM2.5-2.6B and LFM2.5-2.6B-GGUF, a family of hybrid models designed for efficient on-device deployment. These models boast a 128K context window and advanced agentic capabilities, making them competitive with larger models in tasks like tool use and instruction following. The models are optimized for efficient inference, achieving high token generation speeds with minimal memory usage, and are compatible with various popular inference providers and local applications. AI
IMPACT These models could accelerate the adoption of capable AI agents on consumer hardware and edge devices.
RANK_REASON New model release from a frontier lab. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Read on Hugging Face Trending Models →
- Docker
- Google Colab
- Kaggle
- LFM2.5-2.6B
- LiquidAI
- LiquidAI/LFM2.5-2.6B
- OpenAI
- SGLang
- transformers
- vLLM
- Hugging Face
- Jan
- LiquidAI/LFM2.5-2.6B-GGUF
- llama.cpp
- LM Studio
- Ollama
- Raspberry Pi
- Unsloth Studio
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →