🔥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

|￣￣￣￣￣￣￣￣￣￣￣￣￣￣| | lms get devstral-small-2505 | |＿＿＿＿＿＿＿＿＿＿＿＿＿＿| (\__/) || (•ㅅ•) || / づ

Seeking 👀🐳

"lms chat" to use local models in terminal. supports unix pipes cat info.txt | lms chat -p "summarize this" | wc -w

Now updated with MLX quants too

DeepSeek's distilled new R1 AI model can run on a single GPU | TechCrunch techcrunch.com/2025/05/29/dee…

DeepSeek has just released a powerful new 8B model 🔥 This means you can run it locally and for free on a laptop with zero limitations. You just need LM Studio and 4Gb of RAM. The few quick steps below:

The future is multi modal? 🤔 We've been working to rearchitect LM Studio's multi modal MLX engine to increase stability and bring previously text-only model features to vision models, like text prompt caching and context processing updates. Check out the technical writeup ↓

Better together 🤝 LM Studio's new mlx-engine architecture is an effort to unify the brilliant work of Awni Hannun Angelos Katharopoulos (mlx-lm), Prince Canuma (mlx-vlm) and community contributors. This pattern is designed to be extended and we have a good first issue on the repo! 🍎

DeepSeek’s new R1-0528-Qwen3-8B is the most intelligent 8B parameter model yet, but not by much: Alibaba’s own Qwen3 8B is just one point behind Alongside last week’s R1-0528 launch, DeepSeek released a distilled 8B model that aims to bring the advanced reasoning capabilities

yags Nice! Here’s a pic of my 512GB Local LLM rig powered by LM Studio and MLX 😝