正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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.

LM Studio

54,790 subscribers

46,015 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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! 🤯

LM Studio

30,165 次观看 • 1 年前

🔥 DFlash x MLX is happening! Shoutout to Arya Manjaramkar for the early work on this. We're building on the momentum. Native MLX support, more models (Qwen3.5), up to 4x faster. Lossless! 👉

🔥 DFlash x MLX is happening! Shoutout to Arya Manjaramkar for the early work on this. We're building on the momentum. Native MLX support, more models (Qwen3.5), up to 4x faster. Lossless! 👉

Zhijian Liu

214,623 次观看 • 2 个月前

Jan Desktop v0.7.7 is live 💛 This update brings native MLX support on macOS, a broader UX and UI refresh across the app, and better support for developer workflows. You can now upload files in Projects, use the local API server with both local and remote models, and work more smoothly with tools like Claude Code and other CLIs. Update your Jan or download the latest version at

Jan Desktop v0.7.7 is live 💛 This update brings native MLX support on macOS, a broader UX and UI refresh across the app, and better support for developer workflows. You can now upload files in Projects, use the local API server with both local and remote models, and work more smoothly with tools like Claude Code and other CLIs. Update your Jan or download the latest version at

👋 Jan

28,378 次观看 • 4 个月前

Today I'm launching a very early release of MLX Model Manager ( A Swift package for quickly and easily adding LLM/VLMs with just a couple of lines of code into your MacOS/iOS applications for local and private inferencing. This is built on the amazing work of the MLX team & what they have done with MLX Model Manager unifies the work they have done with MLXLLM as well as MLXVLM into one package with added abstractions to simplify the usage. I've also added support for Google's new Paligemma2 Vision Model ( You can see a demonstration in the video below! Huge shoutout to Awni Hannun for the creation of MLX, David Koski on leading the charge for MLXVLM and Prince Canuma for the creation of MLX-VLM. Three massive pillars in the MLX community among many others.

Today I'm launching a very early release of MLX Model Manager ( A Swift package for quickly and easily adding LLM/VLMs with just a couple of lines of code into your MacOS/iOS applications for local and private inferencing. This is built on the amazing work of the MLX team & what they have done with MLX Model Manager unifies the work they have done with MLXLLM as well as MLXVLM into one package with added abstractions to simplify the usage. I've also added support for Google's new Paligemma2 Vision Model ( You can see a demonstration in the video below! Huge shoutout to Awni Hannun for the creation of MLX, David Koski on leading the charge for MLXVLM and Prince Canuma for the creation of MLX-VLM. Three massive pillars in the MLX community among many others.

Kunal Batra

104,815 次观看 • 1 年前

Exciting news! The Spatial Gallery app and the Apple Vision Pro app for iPhone are now available! Update to iOS 18.4 Beta 2 and visionOS 2.4 Beta 2 to try them out.

Exciting news! The Spatial Gallery app and the Apple Vision Pro app for iPhone are now available! Update to iOS 18.4 Beta 2 and visionOS 2.4 Beta 2 to try them out.

Justin Ryan ᯅ

15,536 次观看 • 1 年前

Got continuous batching working with SSMs in mlx-lm. Here's four OpenCode agents simultaneously running Nvidia's Nemotron Nano on 64GB M4 Max. This is a nice model for smaller machines since it's MoE + hybrid attention (small cache).

Got continuous batching working with SSMs in mlx-lm. Here's four OpenCode agents simultaneously running Nvidia's Nemotron Nano on 64GB M4 Max. This is a nice model for smaller machines since it's MoE + hybrid attention (small cache).

Awni Hannun

35,078 次观看 • 5 个月前

Qwen2.5-VL now on MLX 🚀 You can now run inference or train it locally on your Mac using MLX. > pip install -U mlx-vlm Note: Video support is coming shortly :) Model cards 👇🏾

Qwen2.5-VL now on MLX 🚀 You can now run inference or train it locally on your Mac using MLX. > pip install -U mlx-vlm Note: Video support is coming shortly :) Model cards 👇🏾

Prince Canuma

29,952 次观看 • 1 年前

First steps for a specialized DeepSeek v4 Flash inference engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.

First steps for a specialized DeepSeek v4 Flash inference engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.

antirez

14,176 次观看 • 2 个月前

DeepSeek-Prover (4-bit 7B) running at 114 toks/sec in MLX LM on an M2 Ultra Thanks to for the port!

DeepSeek-Prover (4-bit 7B) running at 114 toks/sec in MLX LM on an M2 Ultra Thanks to for the port!

Awni Hannun

16,078 次观看 • 1 年前

Code Connect is now out of beta and with new improvements (!!) → Code Connect snippets in the component playground → A new and faster setup process → Support for React, React Native, SwiftUI, Compose, and more coming soon → Now available for supported UI Kits #Config2024

Code Connect is now out of beta and with new improvements (!!) → Code Connect snippets in the component playground → A new and faster setup process → Support for React, React Native, SwiftUI, Compose, and more coming soon → Now available for supported UI Kits #Config2024

Figma

66,435 次观看 • 2 年前

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

LM Studio

73,791 次观看 • 1 年前

BREAKING: xAI has released a major update for the Grok App with a lot of improvements to Imagine. Please update your app to the latest version available on the AppStore.

BREAKING: xAI has released a major update for the Grok App with a lot of improvements to Imagine. Please update your app to the latest version available on the AppStore.

DogeDesigner

58,289 次观看 • 8 个月前

Apple wasn’t kidding, the iPhone 17 Pro is really built for running LLMs Here’s LFM2 8B A1B by running on-device with MLX in Locally AI - Local AI Chat, the iPhone runs the 8B model with zero struggle Thanks Prince Canuma for the port to MLX, it made the MLX Swift port possible

Apple wasn’t kidding, the iPhone 17 Pro is really built for running LLMs Here’s LFM2 8B A1B by running on-device with MLX in Locally AI - Local AI Chat, the iPhone runs the 8B model with zero struggle Thanks Prince Canuma for the port to MLX, it made the MLX Swift port possible

Adrien Grondin

493,442 次观看 • 8 个月前

Plasticity's newest beta release (v25.2.0-beta.3) has some exciting features. One of which is the inclusion of ambient occlusion in render mode. This BETA release is available for all Studio owners. #plasticity3d #plasticity #cadforartists #plasticitybeta

Plasticity's newest beta release (v25.2.0-beta.3) has some exciting features. One of which is the inclusion of ambient occlusion in render mode. This BETA release is available for all Studio owners. #plasticity3d #plasticity #cadforartists #plasticitybeta

Plasticity

11,468 次观看 • 1 年前

chat app with the new mlx foundation models

chat app with the new mlx foundation models

xavier

58,451 次观看 • 1 年前

This week, we released the latest #MegascansTrees: Common Hazel pack - now available to download on the Unreal Engine Marketplace. For more insight, watch the latest New in #Megascans episode featuring our trees packs: #quixel

This week, we released the latest #MegascansTrees: Common Hazel pack - now available to download on the Unreal Engine Marketplace. For more insight, watch the latest New in #Megascans episode featuring our trees packs: #quixel

Quixel

25,866 次观看 • 3 年前

Playing with Qwen3-TTS is and MLX-Audio locally on Mac Studio M3 Ultra 🔥 Amazing model by Qwen and great work by Prince Canuma bringing this magic to MLX! Tuning the voice with instructions feels like magic! Command and prompts to run it are in the video.

Playing with Qwen3-TTS is and MLX-Audio locally on Mac Studio M3 Ultra 🔥 Amazing model by Qwen and great work by Prince Canuma bringing this magic to MLX! Tuning the voice with instructions feels like magic! Command and prompts to run it are in the video.

Ivan Fioravanti ᯅ

35,720 次观看 • 5 个月前

【📢】 The newest VTube Studio beta and Live2D Cubism alpha now let you record animations directly in the Live2D Cubism Editor using VTube Studio tracking data!! ✨ Now available for beta testing!! ✨ For more info, see:

【📢】 The newest VTube Studio beta and Live2D Cubism alpha now let you record animations directly in the Live2D Cubism Editor using VTube Studio tracking data!! ✨ Now available for beta testing!! ✨ For more info, see:

VTube Studio

82,796 次观看 • 2 年前

How much faster is the new MacBook Pro for AI inference? M4 Max is 27% faster with 72 tok/sec compared to 56 tok/sec of the M3 Max with MLX running Gemma 2 9B (4bit). The 27% speedup is the same with Llama-3.2-1b, Llama-3.2-3b and others. Next up: EXO Labs M4 cluster.

How much faster is the new MacBook Pro for AI inference? M4 Max is 27% faster with 72 tok/sec compared to 56 tok/sec of the M3 Max with MLX running Gemma 2 9B (4bit). The 27% speedup is the same with Llama-3.2-1b, Llama-3.2-3b and others. Next up: EXO Labs M4 cluster.

Alex Cheema

529,673 次观看 • 1 年前