Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Today we're excited to introduce Multi-Model Sessions! — Load & prompt multiple local LLMs simultaneously — Use the API to build networks, pipelines of LLMs that can talk with each other — Use the new JSON Mode to constrain each model's output format LM Studio 0.2.17 is available for... show more

LM Studio

59,032 subscribers

89,817 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

LM Studio2 years ago

Enforce JSON output from loaded models

LM Studio2 years ago

The following video shows a more complete workflow: 1. Choose which models to load 2. Configure each one with a different preset, system prompt, and optionally a JSON Schema 3. Use the Multi Model Prompter for quick evaluations 4. Use the Local Server (OpenAI-like interface) to build software that utilizes multiple LLMs at runtime

LM Studio2 years ago

You can already use Multi-LLM Sessions in AutoGen! @pyautogen Thanks to @ekzhu and @Chi_Wang_ .

Fredo Ayala 🏴‍☠️2 years ago

Anyway we could get this as an easy to deploy docker image on hugging face space ?

AI Turbo dev ☮️🇿🇦 🇵🇱 🖖2 years ago

StarCoder2 support for the win

aaron - /acc of some sort2 years ago

Does this mean it works with hermes-2-pro function calling and Jason output

Lumo 🌕2 years ago

Congratulations, this is massive!

Roman Pshichenko2 years ago

That’s a great update. Keep up the awesome work

LM Studio2 years ago

🦾

eduardo2 years ago

Great update. Looking forward to prompting multiple LLMs locally.

Related Videos

We’re excited to introduce RAGs v2 - build, customize, and use multiple ChatGPTs over your data, all with natural language 💬 A huge upgrade vs. the initial launch: 💫 Easily create multiple RAG pipelines and save them 💫 Easily swap between and customize each one (e.g. over different data, or w/ different system prompts) 💫 Delete unused RAG pipelines 💫 (dev quality) added much-needed linting/CI Check out the video 🎥 for details. It’s super easy to setup and use. Some additional features: 🧠 Supports a lot of LLMs both for building RAG and within each RAG pipeline 🌐 Supports loading load files or web pages. Check out our repo here:

We’re excited to introduce RAGs v2 - build, customize, and use multiple ChatGPTs over your data, all with natural language 💬 A huge upgrade vs. the initial launch: 💫 Easily create multiple RAG pipelines and save them 💫 Easily swap between and customize each one (e.g. over different data, or w/ different system prompts) 💫 Delete unused RAG pipelines 💫 (dev quality) added much-needed linting/CI Check out the video 🎥 for details. It’s super easy to setup and use. Some additional features: 🧠 Supports a lot of LLMs both for building RAG and within each RAG pipeline 🌐 Supports loading load files or web pages. Check out our repo here:

LlamaIndex 🦙

124,174 views • 2 years ago

LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on LM Studio: auto-discovering your models, loading them on demand with the right context size, and using the right reasoning level for each model.

LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on LM Studio: auto-discovering your models, loading them on demand with the right context size, and using the right reasoning level for each model.

Nous Research

185,570 views • 2 months ago

local LLMs on Mac are getting good. but the workflow around models is still messy. you have models in: •⁠ ⁠LM Studio •⁠ ⁠Ollama •⁠ ⁠Hugging Face cache •⁠ ⁠random folders •⁠ ⁠manual downloads and every runtime expects something slightly different. we built ModelHub to clean up this layer. it’s a native macOS menu bar app for discovering, downloading, and managing local LLMs. not a replacement for Ollama, oMLX or LM Studio. it sits beside them. Ollama = run models MLX = Apple Silicon acceleration LM Studio = local model workspace Hugging Face = model ecosystem ModelHub = model discovery + management layer we’re live on Product Hunt today. would love feedback from people running local models on Mac.

local LLMs on Mac are getting good. but the workflow around models is still messy. you have models in: •⁠ ⁠LM Studio •⁠ ⁠Ollama •⁠ ⁠Hugging Face cache •⁠ ⁠random folders •⁠ ⁠manual downloads and every runtime expects something slightly different. we built ModelHub to clean up this layer. it’s a native macOS menu bar app for discovering, downloading, and managing local LLMs. not a replacement for Ollama, oMLX or LM Studio. it sits beside them. Ollama = run models MLX = Apple Silicon acceleration LM Studio = local model workspace Hugging Face = model ecosystem ModelHub = model discovery + management layer we’re live on Product Hunt today. would love feedback from people running local models on Mac.

sabesh 📟

31,497 views • 1 month ago

Run Orpheus — the state-of-the-art TTS — on your local PC! Orpheus-FastAPI is a high-performance TTS app with OpenAI-compatible API, running efficiently with LM Studio backend. And Death wrote this 1-click launcher for us! Cross platform (Mac, Linux, Windows)

Run Orpheus — the state-of-the-art TTS — on your local PC! Orpheus-FastAPI is a high-performance TTS app with OpenAI-compatible API, running efficiently with LM Studio backend. And Death wrote this 1-click launcher for us! Cross platform (Mac, Linux, Windows)

cocktail peanut

30,930 views • 1 year ago

Function calling is a powerful way to extend the capabilities of LLMs and AI agents by letting them use external tools. Our new short course Function calling and Data Extraction with LLMs, created with @NexusflowX and taught by Jiantao Jiao and Venkat, demonstrates how to prompt LLMs to form calls to external functions. You'll work with NexusRavenV2-13B, a 13B parameter open-source model that excels in function calling tasks while still being small enough to host locally. Learn to use function calling to extract structured data from unstructured text and access web APIs, and build an end-to-end application that processes customer service transcripts. You'll learn how to build LLM-powered applications that can analyze feedback, automate data entry, and enhance search. Please get started here:

Function calling is a powerful way to extend the capabilities of LLMs and AI agents by letting them use external tools. Our new short course Function calling and Data Extraction with LLMs, created with @NexusflowX and taught by Jiantao Jiao and Venkat, demonstrates how to prompt LLMs to form calls to external functions. You'll work with NexusRavenV2-13B, a 13B parameter open-source model that excels in function calling tasks while still being small enough to host locally. Learn to use function calling to extract structured data from unstructured text and access web APIs, and build an end-to-end application that processes customer service transcripts. You'll learn how to build LLM-powered applications that can analyze feedback, automate data entry, and enhance search. Please get started here:

Andrew Ng

110,420 views • 2 years ago

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 views • 4 months ago

today we're launching opencode zen zen provides the best LLMs for coding ALWAYS in the best possible configuration no more "did claude get dumber?" no more being routed to a crappy provider and we're giving it to you at cost and you can use it anywhere that enough for you?

today we're launching opencode zen zen provides the best LLMs for coding ALWAYS in the best possible configuration no more "did claude get dumber?" no more being routed to a crappy provider and we're giving it to you at cost and you can use it anywhere that enough for you?

dax

199,278 views • 9 months ago

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks AI. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks AI. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

elvis

39,452 views • 4 months ago

Today we're excited to launch Action: a Claude computer use launcher for macOS. Action is a macOS launcher that can take actions (click, type, and more) on your Mac using Claude’s computer use API. The interface is a floating window triggered by a keyboard shortcut, similar to Spotlight. This lets you see what the model outputs as it performs actions.

Today we're excited to launch Action: a Claude computer use launcher for macOS. Action is a macOS launcher that can take actions (click, type, and more) on your Mac using Claude’s computer use API. The interface is a floating window triggered by a keyboard shortcut, similar to Spotlight. This lets you see what the model outputs as it performs actions.

Lawrence Chen

21,622 views • 1 year ago

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 views • 1 year ago

Meet #DBRX: a general-purpose LLM that sets a new standard for efficient open source models. Use the DBRX model in your RAG apps or use the DBRX design to build your own custom LLMs and improve the quality of your GenAI applications.

Meet #DBRX: a general-purpose LLM that sets a new standard for efficient open source models. Use the DBRX model in your RAG apps or use the DBRX design to build your own custom LLMs and improve the quality of your GenAI applications.

Databricks

327,704 views • 2 years ago

Artifacts, but 100% Open Source, Private & Local. Open WebUI has released a game changer update---"Artifacts". Instead of proprietary LLMs, you can now use fully LOCAL and PRIVATE LLM via ollama to build apps! Here I use Qwen 2.5 32B to build a game of life app.

Artifacts, but 100% Open Source, Private & Local. Open WebUI has released a game changer update---"Artifacts". Instead of proprietary LLMs, you can now use fully LOCAL and PRIVATE LLM via ollama to build apps! Here I use Qwen 2.5 32B to build a game of life app.

cocktail peanut

60,158 views • 1 year ago

Bitwig Studio 5.3 is out now! Download it today to get new drum devices, step sequencer, and workflow improvements to the transport section and your audio i/o configuration – like the ability to use multiple audio interfaces simultaneously. Learn more:

Bitwig Studio 5.3 is out now! Download it today to get new drum devices, step sequencer, and workflow improvements to the transport section and your audio i/o configuration – like the ability to use multiple audio interfaces simultaneously. Learn more:

Bitwig

10,486 views • 1 year ago

We're excited to announce Stream's new Video API, which is now available for general use! 🎥🚀 The video API aims to make it easier for developers to build live in-app video calling, audio rooms, and live streaming. 🎧 During our eight-month beta program, our team worked closely with several companies to help integrate, test, and develop our API and SDKs. Learn more here:

We're excited to announce Stream's new Video API, which is now available for general use! 🎥🚀 The video API aims to make it easier for developers to build live in-app video calling, audio rooms, and live streaming. 🎧 During our eight-month beta program, our team worked closely with several companies to help integrate, test, and develop our API and SDKs. Learn more here:

Stream

134,124 views • 2 years ago

Today was the premiere of the Multiple Robots Update! 🤖🤖🤖🤖 Yes they can insult each other and start punching and kicking each other, but only if you set their system prompt to that!

Today was the premiere of the Multiple Robots Update! 🤖🤖🤖🤖 Yes they can insult each other and start punching and kicking each other, but only if you set their system prompt to that!

MyRobot Dev

98,528 views • 7 months ago

🚨 Announcing Abacus AI SuperComputer - Build Any Cloud Service With A Single Prompt - build or host any cloud app, API or service - spin up local LLMs - always on agents including Hermes/Claw - use cloud storage and databases - work with Claude or Codex - scale to billions of AI agents Simply chat with the super computer to build, host or run anything!!

🚨 Announcing Abacus AI SuperComputer - Build Any Cloud Service With A Single Prompt - build or host any cloud app, API or service - spin up local LLMs - always on agents including Hermes/Claw - use cloud storage and databases - work with Claude or Codex - scale to billions of AI agents Simply chat with the super computer to build, host or run anything!!

Bindu Reddy

33,188,558 views • 1 month ago

How can business leaders, not just coders, build AI business applications with LLMs? Our new short course, created with Microsoft, is out! In How Business Thinkers Can Start Building AI Plugins With Semantic Kernel, taught by John Maeda, you'll learn to use Semantic Kernel and build an AI planner that can automatically select the plugins it needs to create multi-step plans with sophisticated logic. Please sign up here:

How can business leaders, not just coders, build AI business applications with LLMs? Our new short course, created with Microsoft, is out! In How Business Thinkers Can Start Building AI Plugins With Semantic Kernel, taught by John Maeda, you'll learn to use Semantic Kernel and build an AI planner that can automatically select the plugins it needs to create multi-step plans with sophisticated logic. Please sign up here:

Andrew Ng

331,649 views • 2 years ago

hi! Open Interpreter 0.2.0—The New Computer Update—is out today. everything's new. - OS Mode lets vision models operate your computer - We included a new model for precise GUI control - We're launching a Computer API for LLMs ↓

hi! Open Interpreter 0.2.0—The New Computer Update—is out today. everything's new. - OS Mode lets vision models operate your computer - We included a new model for precise GUI control - We're launching a Computer API for LLMs ↓

killian

421,657 views • 2 years ago

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Tushar Verma

137,517 views • 4 months ago

➊ Let's Build Your Bot: Go to Grok and use this prompt: "Create a bot that scans Twitter for memecoin symbols. Use the GMGN API and to track top Solana memecoins in a local database."

➊ Let's Build Your Bot: Go to Grok and use this prompt: "Create a bot that scans Twitter for memecoin symbols. Use the GMGN API and to track top Solana memecoins in a local database."

Woody

45,668 views • 1 year ago