Foundry Local Release 0.8.94

Foundry Local Release Notes: v0.8.94 🚀

✨ New Features

Improve performance for multi-turn conversations, especially time to first token, with the addition of the continuous decoding feature. Only new tokens are sent to the model instead of the entire conversation. The previous inputs and responses are saved by the model in the KV-cache.

Website showing full model list with hardware variants: https://foundrylocal.ai/models

🐛 Bug fixes

• Foundry Local now defaults to --default-log-level instead of Information if --log-level is not provided. Foundry Local also elevates the level with which some errors were being written with from Information to Error.
• #265
• #263
• #71

📝 Known issues

• This version is not supported on macos. Please use the previous release for macos. Support coming soon!
• If model is not found in the catalog, instead of showing a warning / suggestion message and gracefully exiting, an exception
  is thrown.
• When the context length is exhausted (set by the max_length value), instead of showing a warning / error message, an exception is thrown

Foundry Local Release 0.7.120

Foundry Local Release Notes: v0.7.120 🚀

✨ New Features

Improvements to NPU accelerator (execution provider) download and registration user experience

🐛 Bug fixes

#257
#259
#263
#264

Foundry Local Release 0.7.117

Foundry Local Release Notes: v0.7.117 🚀

✨ New Features

• Support for AMD and Intel NPUs, and more Qualcomm NPU models coming very soon
• Pluggable execution providers, downloaded at runtime on Windows for AMD NPUs, Intel NPUs, NVIDIA GPUs, and Qualcomm NPUs
• Filter models by device and provider

🐛 Bug fixes

• #221
• #225
• #233

Foundry Local 0.6.87 Release

Foundry Local Release Notes: v0.6 🚀

✨ New Features

Support new OAI-OSS-20B model!

limitation: only NVidia GPU with 16GB VRAM currently supported. Other GPU and macOS support coming soon.

9/12/2025: updating python SDK to fix compatibility issue.

Foundry Local 0.5.117 Release

Foundry Local Release Notes: v0.5 🚀

This release introduces several new features, bug fixes, and improvements to enhance your experience with Foundry Local.

✨ New Features

• Introduction of the C# SDK: Microsoft Learn C# SDK Docs

🐛 Bug Fixes

#144 Streaming chunks have the same id
#162 Foundry Local supports BYOM (Bring your own model) correctly again.

• Fixed an empty prompt bug
• Fixed a buffer overrun bug

⚙️ Improvements

Improvements to and expansion of logging and telemetry

Notes:

• The previous SDK packages are still the latest ones. Install them using: pip install foundry-local sdk or npm install foundry-local-sdk

Foundry Local 0.4.91 Release

Foundry Local Release Notes: v0.4 🚀

This release introduces several new features, bug fixes, and improvements to enhance your experience with Foundry Local.

✨ New Features

• New Chat Command: You can now start a new chat within an interactive session using the /new command. This will clear your current chat history, allowing for a fresh start.
• Show License: We've added a foundry --license command to make it easy to display the license information for the Foundry CLI.

🐛 Bug Fixes

• Force Download: A fix has been implemented for the foundry model download <model> --force command to ensure that any previous downloads are completely cleaned up.
• Multi-GPU: A fix has been implemented where foundry model run <model>-cuda-gpu would error on a computer with more than one GPU card.

⚙️ Improvements

• Delete All Models: You now have the ability to delete all models from the cache at once by specifying * as the model name.
• Model Alias Support: We've expanded support for model aliases to the model unload and cache remove commands. This allows for the selection of the best model for your local machine, similar to how it works with model download, model load, and model run.
• Remove All Models with Alias: The --all option has been added to the model unload and cache remove commands. This allows you to remove all models from the cache that match a specific model alias.
• Interactive Run: The --interactive option has been removed from the run command. A run is now interactive by default unless a --prompt is specified.
• Model ID Output: The model ID will now be displayed when downloading a model using an alias. This provides clarity on which model was selected for download.

Notes:

• The previous SDK packages are still the latest ones. Install them using: pip install foundry-local sdk or npm install foundry-local-sdk

Foundry Local 0.3.9267 Release

Welcome to Foundry Local 🌟 - Public Preview 🎉

As our first public release, we're looking for as much experimentation and feedback as possible.

Please open issues or create discussions to let us know how you can make your Foundry Local experience better - we're very receptive to feedback!