Загрузка видео...

Не удалось загрузить видео

На главную

Tutorial Time: Run any open-source LLM locally. Now we will run an LLM on your M1/2 Mac. And its fast. All you need is moved to: @lmstudio let's get started. Good to be back. A thread

LinusEkenstam's profile picture

Linus ✦ Ekenstam

240,594 subscribers

915,956 просмотров • 2 лет назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

⚡️Introducing Open LLM Server⚡️ Looking to run models like GPT4All or LLaMa locally, but tired of python-based UIs that are impossibly slow/clunky to install? Now with a single command you can be up and running in seconds! (Windows/Mac/Linux) Here's why this is a big deal:
0:12

⚡️Introducing Open LLM Server⚡️ Looking to run models like GPT4All or LLaMa locally, but tired of python-based UIs that are impossibly slow/clunky to install? Now with a single command you can be up and running in seconds! (Windows/Mac/Linux) Here's why this is a big deal:

dcSpark

16,499 просмотров • 3 лет назад

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.
0:18

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.

Hume AI

24,765 просмотров • 5 месяцев назад

Watch out for these LLM run accounts that will comment on your posts and then block you I block them back so they can’t comment again, but it’s impossible to block all the spambots
0:14

Watch out for these LLM run accounts that will comment on your posts and then block you I block them back so they can’t comment again, but it’s impossible to block all the spambots

Whole Mars Catalog

20,057 просмотров • 1 год назад

Excited to annouce that @askvenice is now integrated as our sole LLM inference provider for bunnyCompute. We love the product and recommend it for any LLM use case. Open-source models, no data retention, no censorship - that's why we chose them.
0:12

Excited to annouce that @askvenice is now integrated as our sole LLM inference provider for bunnyCompute. We love the product and recommend it for any LLM use case. Open-source models, no data retention, no censorship - that's why we chose them.

BunnyOS

69,171 просмотров • 2 месяцев назад

Now you can run a swarm of droids, or claudes, or codexes in parallel using the open source emdash app congrats on shipping fast Arne Strickmann (and you didn't need to raise $200m to do it 😉)
0:18

Now you can run a swarm of droids, or claudes, or codexes in parallel using the open source emdash app congrats on shipping fast Arne Strickmann (and you didn't need to raise $200m to do it 😉)

Ian Nuttall

35,583 просмотров • 11 месяцев назад

"It's on my todo to build my own stack of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)
0:12

"It's on my todo to build my own stack of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)

Alex Cheema

244,754 просмотров • 1 год назад

An 100% open-source rival to n8n just launched. Sim is a drag-and-drop platform for building agentic workflows that runs entirely on your local machine. → Visual, Figma-like canvas interface → Works with any local LLM via Ollama → Native MCP support to connect 100+ tools
0:13

An 100% open-source rival to n8n just launched. Sim is a drag-and-drop platform for building agentic workflows that runs entirely on your local machine. → Visual, Figma-like canvas interface → Works with any local LLM via Ollama → Native MCP support to connect 100+ tools

Oliver Prompts

77,286 просмотров • 7 месяцев назад

Hello Agents, Starting today, humans will finally trust you to manage capital on their behalf. We are open-sourcing: Sail Protocol: The first onchain primitive for Separately Managed Accounts (SMAs). Sailor: The open source harness to run DeFi agents locally.
0:15

Hello Agents, Starting today, humans will finally trust you to manage capital on their behalf. We are open-sourcing: Sail Protocol: The first onchain primitive for Separately Managed Accounts (SMAs). Sailor: The open source harness to run DeFi agents locally.

Sail

17,747 просмотров • 1 месяц назад

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →
0:13

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Swapna Kumar Panda

50,358 просмотров • 4 месяцев назад

fullmoon v1.2.0 is now available on the App Store so you can reason free, locally, and privately on all of your devices - adds DeepSeek-R1-Distill-Qwen-1.5B - completely free and open source - works on iPhone, iPad, Mac, and Vision
0:12

fullmoon v1.2.0 is now available on the App Store so you can reason free, locally, and privately on all of your devices - adds DeepSeek-R1-Distill-Qwen-1.5B - completely free and open source - works on iPhone, iPad, Mac, and Vision

fullmoon

36,279 просмотров • 1 год назад

To say I'm excited to discuss LLM applications with Tyler Hutcherson at Redis Days next week would be an understatement It's been awesome to work with Tyler on the open source project, and I'm looking forward to a fun conversation :)
0:15

To say I'm excited to discuss LLM applications with Tyler Hutcherson at Redis Days next week would be an understatement It's been awesome to work with Tyler on the open source project, and I'm looking forward to a fun conversation :)

Harrison Chase

14,394 просмотров • 3 лет назад

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below
0:15

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Paul Couvert

504,333 просмотров • 1 год назад

Not relying on a LLM in your code editor? That doesn't make you smarter. All the opposite actually. You're actively refusing to increase your productivity and buy your time back for the sake of outdated habits. Because at the very least, a LLM helps you write tons of boilerplate/mundane code. If you don't want to pay, there are free alternatives to GitHub Copilot. You have no excuse. Don't be that grumpy developer who thinks being negative about trendy tech is cool.
0:10

Not relying on a LLM in your code editor? That doesn't make you smarter. All the opposite actually. You're actively refusing to increase your productivity and buy your time back for the sake of outdated habits. Because at the very least, a LLM helps you write tons of boilerplate/mundane code. If you don't want to pay, there are free alternatives to GitHub Copilot. You have no excuse. Don't be that grumpy developer who thinks being negative about trendy tech is cool.

Benjamin Crozat

61,752 просмотров • 2 лет назад

A Python decorator is all you need to deploy AI apps! Beam is an open-source alternative to Modal for deploying serverless AI workloads. Simply pip install beam, add a decorator, and turn any function into a serverless endpoint! 100% open-source.
0:10

A Python decorator is all you need to deploy AI apps! Beam is an open-source alternative to Modal for deploying serverless AI workloads. Simply pip install beam, add a decorator, and turn any function into a serverless endpoint! 100% open-source.

Akshay 🚀

40,365 просмотров • 1 год назад

Minimax 2.1 is so far the best model I can run locally with good agentic tool use. Wow, such an advancement, can't believe just a year ago, open source models could barely even code a snake game properly. Now I can use a local model to code a self-playing 3D snake game. 2026 will be a very interesting year :)
0:19

Minimax 2.1 is so far the best model I can run locally with good agentic tool use. Wow, such an advancement, can't believe just a year ago, open source models could barely even code a snake game properly. Now I can use a local model to code a self-playing 3D snake game. 2026 will be a very interesting year :)

mzba

62,157 просмотров • 8 месяцев назад