Klose Li

@lmstudiodevs long time since last mlx updated

LM Studio 0.4.7 Beta (build 3) is now available. This build contains many bug fixes: 🐛🔨 LaTeX ($ signs) rendering, extraneous <think> tags in coding agents, fixes for tool calling parsing, and more! Update in-app or from lmstudio.ai/beta-releases

@ivanfioravanti What do you think of mxfp8 vs. int8? Most quantization relies on int8, but ChatGPT says that mxfp8 has better precision.

Using 4bit coding models locally give you more generation speed, but less precision. This means model and harness will keep iterating on wrongly created file to fix them. TLDR: better using 6bit or above for local coding.

@SkylerMiao7 Do you have plans to release a model under 100B for local deployment and excels at coding tasks?

yep — it began as an experiment. m2.5 is shaping up to be even crazier. we’ll probably run another AMA then😉

@0xSero thank you for your optimization. I have convert the reap-30 into mlx-mxfp4, it works great especially in tool calling.

Hey guys. If any of you have 256gb Mac Studio or Nvidia if you can help me quantize these to GGUF, MLX and AWQ To the best of my ability I fixed the weights, these were the only 2 that are salvageable. But, they’re good. Blog and video tomorrow about why the other one was broken. huggingface.co/0xSero/MiniMax… huggingface.co/0xSero/MiniMax…

@auto_localize @lmstudio @MistralAI The vision API of LM Studio / mlx expects "image_base64":"AAAA..." , but cline provides the official OpenAI format shown as below "image_url":{ "url":"data:image/png;base64,..."} So LM Studio will not parse it.

@lwl53 @lmstudio @MistralAI I am also getting the error while using Cline.

Devstral 2 is now available in MLX on Apple Silicon. Run a local SOTA coding model on your MacBook. Please update to LM Studio 0.3.35 first! Have a nice weekend! 👾

@auto_localize @lmstudio @MistralAI I have the same issue when Cline is using the browser tool

@lmstudio @MistralAI After the update, I started getting the following error for all models. I would appreciate it if you could check 🙏

@yagilb MLX 0.31.0 , mlx-vlm==0.3.4 When will be updated to latest 0.3.5? I would like to try Deepseek-OCR

LM Studio 0.3.31 coming out today LM Studio 0.4.0 beta starts this week

@UnicornBitcoin @HuoQubot

据说比三上悠亚知名度高，真的假的

It’s killing me to delete more than 300 tweets one by one, fxcking the guy hacked my Twitter

国内能上twitter youtube和facebook了！mark一下