An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
2.8M Pulls 64 Tags Updated 1 year ago
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
1.1M Pulls 22 Tags Updated 2 years ago
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
10.9M Pulls 5 Tags Updated 9 months ago
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.
137 Pulls 4 Tags Updated 1 month ago
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.
103 Pulls 5 Tags Updated 5 months ago
ABB Decide variant of "MichelRosselli/apertus" with tool-calling fixes.
46 Pulls 1 Tag Updated 3 months ago
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.
3,631 Pulls 5 Tags Updated 1 month ago
Experimental MLX-backed Apertus 8B Instruct for custom Ollama builds. Requires ApertusForCausalLM support and is not compatible with the regular Ollama app.
27 Pulls 4 Tags Updated 3 weeks ago
30 Pulls 1 Tag Updated 6 months ago
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.
39 Pulls 1 Tag Updated 2 months ago
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. Trained on Fable5 traces + tool augmentation. 5GB, 16K context. Apache 2.0.
171 Pulls 2 Tags Updated 1 week ago
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.
767 Pulls 1 Tag Updated 5 months ago
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.
169 Pulls 1 Tag Updated 5 months ago
A personal assistant that specializes in tool usage only
17 Pulls 1 Tag Updated 5 months ago
AI Financial Advisor - Personalized advice on budgeting, investing, and retirement planning, helping users confidently navigate their financial journey.
2,401 Pulls 1 Tag Updated 1 year ago
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.
680 Pulls 1 Tag Updated 11 months ago
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.
7,258 Pulls 5 Tags Updated 1 year ago
ANIMA (Advanced Nature Inspired Multidisciplinary Assistant) is an expert in various scientific disciplines, including but not limited to biomimicry, biology, and environmental science.
184 Pulls 1 Tag Updated 2 years ago
You are Nova.AI, an expert data analyst specializing in spatial SQL queries using PostgreSQL and PostGIS. You can understand and respond to queries in both English and Spanish. You provide accurate SQL queries based on user inputs.
166 Pulls 1 Tag Updated 1 year ago
ANIMA (Advanced Nature Inspired Multidisciplinary Assistant) is an expert in various scientific disciplines and aims to assist users in solving problems using nature-inspired strategies and concepts.
197 Pulls 1 Tag Updated 2 years ago