LM Studio's banner
LM Studio's profile picture

LM Studio

@lmstudio56,650 subscribers

Discover and run open models 👾 we are hiring https://t.co/2D4CG8GO5m

Shorts

Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1.

Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1.

46,015 görüntüleme

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.

171,577 görüntüleme

Introducing Parallel Requests for MLX! Multiple requests to the same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺

Introducing Parallel Requests for MLX! Multiple requests to the same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺

40,269 görüntüleme

After months of work, and with the help of our awesome community, we're excited to finally share LM Studio 0.3.0! 🎉 🔥 What's new: - Built-in Chat with Documents, 100% offline - OpenAI-like 'Structured Outputs' API with any local model - Total UI revamp (with dark/light/sepia themes) - Load & serve multiple LLMs *on the local network* - Available in 7 languages! 🌎🌍🌏 - Download any supported model from Hugging Face - Update LLM runtimes (llama.cpp) separately from the app ... and tons more goodies! Let us know how you like it! 👾🤝

After months of work, and with the help of our awesome community, we're excited to finally share LM Studio 0.3.0! 🎉 🔥 What's new: - Built-in Chat with Documents, 100% offline - OpenAI-like 'Structured Outputs' API with any local model - Total UI revamp (with dark/light/sepia themes) - Load & serve multiple LLMs *on the local network* - Available in 7 languages! 🌎🌍🌏 - Download any supported model from Hugging Face - Update LLM runtimes (llama.cpp) separately from the app ... and tons more goodies! Let us know how you like it! 👾🤝

142,471 görüntüleme

Thinking...

Thinking...

96,204 görüntüleme

LM Studio 0.3.10 is here with 🔮 Speculative Decoding! This provides inferencing speedups, in some cases 2x or more, with no degradation in quality. - Works for both GGUF/llama.cpp and MLX models! - Easily experiment with different draft models - Visualize accepted draft token % rate - Works in Chat UI and API

LM Studio 0.3.10 is here with 🔮 Speculative Decoding! This provides inferencing speedups, in some cases 2x or more, with no degradation in quality. - Works for both GGUF/llama.cpp and MLX models! - Easily experiment with different draft models - Visualize accepted draft token % rate - Works in Chat UI and API

73,791 görüntüleme

New in LM Studio 0.3.27 💬🔍 Find in current chat, and search all of your chats! ⌘/Ctrl + F ⌘/Ctrl + Shift + F

New in LM Studio 0.3.27 💬🔍 Find in current chat, and search all of your chats! ⌘/Ctrl + F ⌘/Ctrl + Shift + F

28,749 görüntüleme

Counting penguins can be challenging 🧐🐧 New in LM Studio 0.2.9: 🎉 Local & Offline Vision Models! In this demo: the small and impressive Obsidian Vision 3B by Nous Research.

Counting penguins can be challenging 🧐🐧 New in LM Studio 0.2.9: 🎉 Local & Offline Vision Models! In this demo: the small and impressive Obsidian Vision 3B by Nous Research.

70,825 görüntüleme

Happy 2025! Introducing LM Studio 0.3.6 🚀 - New vision models: Qwen2VL and QVQ (both GGUF + MLX) 🤩 - Function Calling API (in beta) 🧰 - New installer on Windows: choose drive (finally 😮‍💨) - In-app updates are much smaller & have a progress bar! 🟩🟩⬜️⬜️ - Update your llama.cpp and MLX engines w/o a full app update 🚂 The demo below uses a 2B model! 🤯

Happy 2025! Introducing LM Studio 0.3.6 🚀 - New vision models: Qwen2VL and QVQ (both GGUF + MLX) 🤩 - Function Calling API (in beta) 🧰 - New installer on Windows: choose drive (finally 😮‍💨) - In-app updates are much smaller & have a progress bar! 🟩🟩⬜️⬜️ - Update your llama.cpp and MLX engines w/o a full app update 🚂 The demo below uses a 2B model! 🤯

30,165 görüntüleme

.AI at Meta's Llama 4 Scout ripping 42.27 tok / sec on M2 Ultra Mac Studio

.AI at Meta's Llama 4 Scout ripping 42.27 tok / sec on M2 Ultra Mac Studio

19,587 görüntüleme

Videos

Daha fazla içerik yok.