AI Model / Educational Tutor LLM
A 1.26B academic tutor model from Zyora Labs, built from scratch and tuned for concept-first explanations in English, Tamil, and Hindi.
The page clearly presents a real AI model with a defined use case, architecture details, training data, benchmark results, and example Hugging Face loading code. It also states the model is a from-scratch tutor model rather than a fine-tune of an existing base, which makes it useful for AI builders and users looking for an educational LLM.
The page does not show a live demo, licensing details beyond the tag, or a full evaluation table for the reported benchmarks. It also leaves open how well the model performs in real tutoring use beyond the sample prompt and brief intended-use note.
Last evaluated 28 days ago. Current rank #787. Down 6 spots in the rankings.
A 150M ModernBERT-based token classification model that extracts verbatim evidence spans for RAG and related pipelines, reducing the need for an LLM call to highlight answers.
JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.
An open-source 26M parameter function-calling model designed to run on very small devices, with a local quickstart, Python usage, and a playground for testing and finetuning.
An open 45M-parameter agentic LLM for tiny devices, built for tool calling, device use, and structured extraction. It ships as a 14 MB binary and is positioned for phones, wearables, smart home devices, robots, and other low-RAM hardware.
