IFM has released several new models, including K2-Horizon-MoVA-36B-A4B and K2-Horizon-7B, available on Hugging Face. These models offer large context windows and are designed for various applications, with detailed instructions provided for integration with popular libraries and inference providers like Transformers, vLLM, and SGLang. The K2-Horizon-MoVA-36B-A4B model, in particular, is highlighted for its performance at a smaller active parameter count, competing with larger models and even closed-source frontier models. AI
IMPACT These releases provide new options for developers and researchers, particularly those needing large context windows or efficient MoE architectures.
RANK_REASON Multiple model releases from IFM, including MoVA and 7B variants, with detailed integration guides.
Read on Hugging Face Trending Models →
- Docker
- Google Colab
- Hugging Face
- IFM/K2-Horizon-MoVA-36B-A4B
- K2-Horizon-MoVA-36B-A4B
- Kaggle
- MOVA
- OpenAI
- SGLang
- transformers
- vLLM
- IFM Paris
- IFM/K2-Horizon-7B
- IFM/K2-Horizon-MoVA-36B-A4B-GGUF
- K2-Horizon-7B
AI-generated summary · Google Gemini · from 6 sources. How we write summaries →