An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
Experimental MLX-backed Apertus v1.1 Mini Instruct models for custom Ollama builds. Known issue: the current Apertus v1.1 Mini artifacts can produce nonsensical chat
Apertus-v1.1 is a series of highly efficient, 0.5-4B billion parameter language models designed to extend the fully-open and compliant Apertus ecosystem to highly constrained hardware environments.
Experimental MLX-backed Apertus 8B Instruct for custom Ollama builds. Requires ApertusForCausalLM support and is not compatible with the regular Ollama app.
Apertus-SEA-LION-v4-8B-IT is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
ABB Decide variant of "MichelRosselli/apertus" with tool-calling fixes.
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.
A specialized MySQL performance tuning assistant built on top of qwen3-coder:480b-cloud. Drop in a slow query or EXPLAIN output — get back exact indexes and reasoning, no fluff.
Perfect censorship bypass (5.0/5) + superior tool use (5.0/5). 13.8/15 total. Best-in-class for shell commands, API calls, Docker, K8s. 5GB, 16K context. Apache 2.0.
qwen2.5-auditor is a local Ollama model wrapper built from qwen2.5-coder and tuned for security-focused code review and static analysis; it adopts a strict “Astra” system persona to act like a security engineer/bug-bounty auditor.
The **Llama-3.1-8B-Instruct-STO-Master** is a high-performance fine-tune of Meta's Llama-3.1-8B-Instruct. This model represents the "Master Version" (Model E) of an extensive research project aimed at pushing the boundaries of 8B parameter architectures.
A personal assistant that specializes in tool usage only
AI Financial Advisor - Personalized advice on budgeting, investing, and retirement planning, helping users confidently navigate their financial journey.
This model is an Ollama version of heydariAI-persian-embeddings from Hugging Face. This is fine-tuned version of xlm-roberta-base, specifically trained on a massive corpus of Persian data to create high-quality contextual embedding for Persian usages.
Moonlight, a 3B/16B-parameter Mixture-of-Expert (MoE) model trained with 5.7T tokens using Muon. Their "model improves the current Pareto frontier, achieving better performance with much fewer training FLOPs compared to prior models."
The Llama 4 models are Meta's flagship LLMs. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text understanding and generation.
ANIMA (Advanced Nature Inspired Multidisciplinary Assistant) is an expert in various scientific disciplines, including but not limited to biomimicry, biology, and environmental science.