//////////// LLM Model //////////// Baichuan-7B (by 百川智能) Claude - Claude can help with use cases including summarization, search, creative and collaborative writing, Q n A, coding, and more. 100K tokens context window Claud 3: 200K tokens context window [Google] Gemini Gemini 1.5: 1M tokens context window [Meta] Llama 13B [Meta] Llama 2 4K tokens context window [Meta] Llama 3.1 405B 128K tokens context window [Microsoft] Phi-3.5-mini-instruct MiniCPM-2B (by 面壁智能 and 清华大学自然语言处理实验室) [nVidia] Mistral-NeMo-Minitron-8B-Base [nVidia] llama-3.1-nemotron-70b-instruct [OpenAI] GPT4 8K/32K tokens context window [OpenAI] ChatGPT (by OpenAI) OmniLMM //////////// LLM Server //////////// LM Studio - Discover, download, and run local LLMs Microsoft's Phi-3 and MetaAI's Llama 3 are supported Ollama - Get up and running with large language models. Run Llama 3, Phi 3, Mistral, Gemma, and other models.