Mega4alik/ollm

Inference for large-context models on consumer GPUs

View on index · View in 3D Map

Related repos

• open-weight GPT models for reasoning and agent tasks
• Inference engine for infinite context lengths
• Modern client for running Ollama AI models locally with a simple interface
• Ollama client for managing and chatting with local AI models
• open-source large language model for reasoning, coding, and agents
• Fast and small JavaScript tokenizer for OpenAI models
• Runs large language models locally without internet or GPUs
• Runs large language models locally
• Persistent memory for AI agents