🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

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

DeepSeek R1 Distilled models are now available in LM Studio! 1.5B, 7B, 8B, 13B, 14B, 32B, and 70B variants. Please update to LM Studio 0.3.7 first. Let's go! 🚀

✨You can now connect AI chat to locally hosted models via LM Studio in JetBrains AI Assistant! Configure the connection in AI Assistant’s settings to gain full control of your AI experience. Check out this and other model updates here: jb.gg/rowjbz

openai/o3-mini-GGUF? 🥹 👉👈

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

We just released LM Studio 0.3.10 with Speculative Decoding support! It's a technique that pairs together a large model, and a more efficient (smaller) "draft" model that can generate tokens fast (draft generation). The larger model then verifies/rejects the draft tokens. If

🚢 LM Studio 0.3.14 is out now with new powerful controls for Multi-GPU setups! > Enable/disable specific GPUs > Choose which GPUs to fill first, second, etc. > Limit offload to Dedicated GPU memory > Bug fixes and more! See it in action in 🧵👇

✨LM Studio 0.3.15 is out now. - Support for NVIDIA RTX 50-series (CUDA 12.8) - GLM-4 enabled in llama.cpp and MLX - New system prompt editor UI 📝 - tool_choice param in OpenAI-like API ... and more 👾 Release notes lmstudio.ai/blog/lmstudio-…

.matt fixed an mlx-engine bug that caused undesired prompt reprocessing. The difference in performance is huge, and the fix is pretty interesting. Check out the PR to see how this issue related to repetition penalty: github.com/lmstudio-ai/ml…

Qwen3 is available on LM Studio in GGUF and MLX! Sizes: 0.6B, 1.7B, 4B, 8B, 14B, 30B MoE, 32B, and 235B MoE Happy Qwen day to all who celebrate! 🎉

Engine update: LM Studio llama.cpp/1.29.0 - Qwen2.5VL now supported in GGUF (h/t Xuan-Son Nguyen) - Support for Nomic AI's new MoE embedding model 🚂 Cmd/Ctrl + Shift + R → Update

Let LM Studio cook 🔥 Ofc cooking with the main ingredients - llama.cpp from ggml 😆😆

LM Studio 0.3.16 is available now! ✨ What's new in this release ↓

MLX-VLM v0.1.27 is here 🚀 Thanks to qnguyen3, Prince Verma, matt from LM Studio and the folks at Cua for the amazing contributions!