LM Studio Beta Releases

🪲 🗣️Please report bugs and feedback to:

• GitHub: lmstudio-ai/lmstudio-bug-tracker
• Discuss on discord: LM Studio Community Discord Server

Download Links - Beta Releases

Version	Build	OS	Arch	Last Updated	Download URL
0.4.17	3	Mac	arm64	06/18/2026	Download
0.4.17	3	Windows	x86_64	06/18/2026	Download
0.4.17	3	Windows	arm64	06/18/2026	Download
0.4.17	3	Linux	x86_64	06/18/2026	Download
0.4.17	3	Linux	x86_64	06/18/2026	Download
0.4.17	3	Linux	arm64	06/18/2026	Download
0.4.17	3	Linux	arm64	06/18/2026	Download

LM Studio is provided under the terms of use.

Release Notes - LM Studio 0.4.17 Build 3 (Beta)

0.4.17 - Release Notes

Build 3

• [LM Studio Engine Protocol] Existing custom Chat Template settings in My Models are now preserved when upgrading
• [LM Studio Engine Protocol] Fixed a bug where unsupported GGUF prediction settings could appear in Chat, My Models, and Server configuration panels
  • Chat Template is now in Load Parameters > Advanced, moved from Prediction Parameters > Prompt Template
  • CPU Thread Pool Size is now in Load Parameters > Advanced, moved from Prediction Parameters > Settings > CPU Threads
  • Speculative Decoding settings are now in Load Parameters > Advanced > Speculative Decoding, moved from Prediction Parameters > Speculative Decoding
• [LM Studio Engine Protocol] Fixed automatic chat title generation for some reasoning models
• [LM Studio Engine Protocol] Fixed a bug where RAG document retrieval could fail with some llama.cpp models
• Fix bug where survey failures due to old ROCm versions led to a stuck state of no-GPUs.

Build 2

• iGPUs while using Vulkan backend are now visible and disabled by default
• AMD Strix Halo machines are now supported via the llama.cpp 2.22.1 runtime
• AMD Radeon AI PRO R9600D and R9700 are now supported via the llama.cpp 2.22.1 runtime
• Fixed bug where AMD GPUs were not detected due to driver updates.

Build 1

• [LM Studio Engine Protocol] Added support for prompt template overrides when loading GGUF models
• [LM Studio Engine Protocol] Added support for load-time speculative decoding with vision model support
• [LM Studio Engine Protocol] Enabled by default for supported llama.cpp models
• [LM Studio Engine Protocol] Fix the bug where model would load on the iGPU while using Vulkan on Windows
• Chat to PDF export updated to include styled markdown
• Added support for Mermaid diagram rendering in chat markdown