Mellum-4b-base is JetBrains' first open-source large language model (LLM) optimized for code-related tasks.
Cost / License
- Free
- Open Source (Apache-2.0)
Application typeApplication types
Platforms
- Self-Hosted
- Python
Czechia
EU

Apps similar to Kolibri include ChatGPT, which has a free version. Other options are Lumo by Proton, DeepSeek, Mistral Vibe and Claude. You can choose from more than 10 Large Language Model (LLM) Tools like Kolibri for the web, Android, iPhone, iPad and Mac.
Mellum-4b-base is JetBrains' first open-source large language model (LLM) optimized for code-related tasks.

The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who...

As part of Meta’s commitment to open science, today we are publicly releasing Llama (Large Language Model Meta AI), a state-of-the-art foundational large language model designed to help researchers advance their work in this subfield of AI.




AI assistant supports complex math, coding, image understanding, and reasoning with up to 128k token processing, short and long chain-of-thought tasks, visual and text input, accurate benchmarks, self-learning ability, and reinforcement learning for improvement.




A family of lightweight, state-of-the art open models built from the same research and technology that we used to create the Gemini models.



Jev is TypeSafe’s first public System One Model, optimized for automation. Send Jev structured questions and get typed decisions with probabilities and confidence that your software can act on.



Provides AI-powered writing tools, image generation, Genmoji, and memory movies; enhances Siri with deeper context and actions; integrates ChatGPT for complex tasks; prioritizes on-device processing for privacy; unifies features across Apple devices with Private Cloud Compute.




AI assistant using hybrid-attention reasoning supports complex, multi-step tasks in multi-agent systems, deep research synthesis, full-stack development, chat, multimodal content, text-to-image generation, privacy settings, distraction-free modes, and cross-device cloud sync.




Open R1 is a community-driven, open-source initiative aimed at replicating the advanced AI capabilities of DeepSeek-R1 through transparent methodologies.
Built end-to-end by Tencent, Hy is a large language model engineered for excellence in content creation, reasoning, code, and conversation. From complex tasks in writing, research, and work, to everyday dialogue, knowledge, and creativity, Hy responds with precision, coherence...
