Foundry Local 0.8.119 Release Notes 🚀

This release is an incremental build, targeting tool calling scenarios.

🐛 Bug fixes

#373 Function specs without parameters cause server error
#372 Tools not indexed in streaming mode

Foundry Local 0.8.117 Release Notes 🚀

This release is an incremental build, targeting tool calling scenarios.

🐛 Bug fixes

#346 Tool calling doesn't return tool_calls results in streaming mode
#341 Exception when network is disconnected

📝 Known issues

#363 Tool calling fails on NVIDIA GPUs.

Foundry Local Release Notes: v0.8.115 🚀

This release is an incremental build targeting tool calling scenarios.

🐛 Bug fixes

#335 Guidance error when tool_choice=required
#336 Foundry Local enforcing "required" field of function parameters

📝 Known issues

#346 Tool calling doesn't return tool_calls results in streaming mode

Foundry Local Release Notes: v0.8.113 🚀

✨ New Features

Add support for tool calling. Models that support tool calling have the supportsToolCalling tag, which is also exposed via the SDKs.

🐛 Bug fixes

Fix crash on context length exhaustion. CLI now exits when context length is exhausted and the REST API returns an error if the request requires more tokens than max_length configuration allows.

📝 Known issues

This release only allows one tool call per request.

Foundry Local Release Notes: v0.8.103 🚀

🔨 Filter out automatic speech recognition models from foundry model list

These models can be listed using the /foundry/list endpoint and run using the standalone SDK

⭐ Sign Up for Foundry Local SDK vNext Private Preview – Fill in form ⭐

Foundry Local Release Notes: v0.8.101 🚀

✨ New Features

Improve performance for multi-turn conversations on macOS, 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.

📝 Known issues

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 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 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 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 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.