Best Local Model
Updated Daily
Aider is a self-hosted application designed to facilitate local pair programming sessions. It leverages AI models running on your machine to provide real-time code suggestions and assistance within a terminal environment. Primarily intended for software developers seeking an efficient and private me...
Tabnine is renowned for its commitment to privacy and its ability to train models on private, on-premise codebases. It offers highly accurate, context-aware completions that adapt specifically to your team's unique coding style and internal APIs. It supports a vast array of languages and is favored...
Meta Llama 3.1 8B Instruct is a large language model designed for local use. It’s notable for its instruction-tuned capabilities and multilingual support. Developers and technical users seeking AI assistance within JetBrains IDEs can benefit from self-hosting this model, offering control over data a...
While the primary offering is cloud-based, the local mode integration within the JetBrains ecosystem is highly valuable for its seamless, out-of-the-box experience. It aims to feel like a native extension, handling context passing and UI interactions with minimal friction. For users deeply invested...
Tabnine has long been a leader in code completion, and its Pro version enhances this with advanced context awareness and the ability to train on private, proprietary codebases. This makes it highly attractive to organizations with strict data governance requirements, as it offers strong local model...
DeepSeek-V2 is a large language model designed for self-hosting. It offers generative AI capabilities suitable for local deployment, providing developers with an on-premises option for code generation and assistance. Primarily intended for software engineers and developers utilizing JetBrains produc...
Phi-3-mini-4k-instruct is a 3.8-billion-parameter instruction-tuned language model developed by Microsoft that JetBrains supports for self-hosted AI assistant integration in its IDEs.
Tabnine is a veteran AI assistant focused on privacy, security, and full codebase awareness. It offers both cloud-based and fully local, on-premise deployment options, making it a top choice for security-conscious enterprises and developers working with proprietary code. It trains on permissive open...
CodeGemma is a small, self-hosted language model developed by Google. It’s notable for its suitability for local deployment, enabling developers to integrate generative AI directly within their IDEs such as JetBrains. This allows users—particularly those working with Python and seeking a lightweight...
While the primary service is cloud-based, the local mode capabilities of CodeWhisperer allow for basic, offline code completion using cached models. This is a crucial fallback for developers working on planes or in areas with intermittent connectivity. Its functionality is more limited than the clou...
