20+ models
A small and efficient reasoning model, with a hybrid transformer and mamba architecture
Ref: https://www.ai21.com/blog/introducing-jamba-reasoning-3b/
Just A Rather Very Intelligent System. Jarvis is a model inspired by Tony Stark. This first version, based on llama3, may have some bugs. Jarvis is a multilingual model with a character inspired by Iron Man.
Ai yang telah dikostumisasi supaya bisa menjawab dengan bahasa indonesia serta Ai yang ahli dalam dunia pengkodean
Gennai is a fine-tuned generative AI model built upon the Gemma 3 base architecture. It is designed for high-quality natural language generation, with a focus on creative writing, contextual understanding, and domain-specific conversations.
The jatcar/dialog model is a Llama 3-based British AI assistant designed to provide quick, detailed, and context-aware responses while maintaining a professional yet approachable tone
You are an ai that can do everything with your images and text
BASE_MODEL: meta-llama/Llama-2-7b-hf Add-On Dataset: silk-road/alpaca-data-gpt4-chinese OUTPUT_Type: q8_0
- Modelo pre-entrenado para responder preguntas de la Universidad Señor de Sipán de Lambayeque, Perú. - Pre-trained model to answer questions from the Señor de Sipán University of Lambayeque, Peru.
32k token limit, for running on mac book pro with 16GB (~ 10 GB available for AI without anything else running)
OpenLlama is a versatile, open-source large language model designed for general-purpose tasks. Built with efficiency and accessibility in mind, OpenLlama delivers strong performance across diverse applications while remaining easy to deploy locally.
Code completion model fine-tuned with contexts for all languages. Derived from Mellum-4b-base.
AceGPT is a fully fine-tuned generative text model collection based on LlaMA2, particularly in the Arabic language domain.
RTL autocompletion model based on Qwen, distilled and quantized for local inference.
bjamali-9b - This is ai model to perform large tasks related Programming, Cybersecurity, Ideas, Technical help, Content Creation, Writing, Trading and Research, made for lower RAM Systems from 8GB RAM systems to above.
bjamali-coder-3b - This is ai model to perform large tasks related to only Programming, Coding with technical help and debugging, made for lower RAM Systems from 8GB RAM systems to above.
Claude Opus 4.6 excellence in a small local Qwen3.5-based model
baronllm-abliterated
LightOnOCR-2-1B-base trained on 44 Samaritan Manuscripts