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

238,736 subscribers

915,828 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

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 • 11 месяцев 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

68,393 просмотров • 22 дней 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

35,523 просмотров • 10 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 - e/acc

243,248 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 • 6 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

15,231 просмотров • 13 дней 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

50,102 просмотров • 3 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

14,379 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

504,191 просмотров • 1 год назад

Now this is something that will take mac users time to get used to. Not only has Apple removed the good-old App menu, the new one needs you to double click to open an app. #macOSTahoe
0:11

Now this is something that will take mac users time to get used to. Not only has Apple removed the good-old App menu, the new one needs you to double click to open an app. #macOSTahoe

Mukul Sharma

19,480 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

QwQ-32B Is Now On ChatLLM! You asked, and we delivered—the world's best open-source model is available for FREE on ChatLLM Teams. If you don't have it, please wait a few minutes. It will take an hour to roll out everywhere. First impressions - it's fast and has good vibes.
0:18

QwQ-32B Is Now On ChatLLM! You asked, and we delivered—the world's best open-source model is available for FREE on ChatLLM Teams. If you don't have it, please wait a few minutes. It will take an hour to roll out everywhere. First impressions - it's fast and has good vibes.

Bindu Reddy

28,419 просмотров • 1 год назад

Get on your hands and knees like a dog! Now... Ohh!! you try to get up? Come on boy, get up! You will have exactly 8 seconds to get back on all fours... like a GOOD boy... understood?
0:12

Sensitive content

Get on your hands and knees like a dog! Now... Ohh!! you try to get up? Come on boy, get up! You will have exactly 8 seconds to get back on all fours... like a GOOD boy... understood?

Femdome Huma

16,718 просмотров • 2 лет 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 • 6 месяцев назад

open-sourced the KOL pricing tool i built for Minara AI growth. paste an X handle, get back in 5 seconds: - tier (trader / NFT / builder / influencer / mass + tool-builder overlay) - cash range + ROI per collab type - claude-drafted DM that quotes their actual recent tweets It's a self-hosted vue app that runs locally on your PC. you will need to fill in your own X & LLM API keys. And all rating records stay on your PC as well. also you can change the KOL type based on your product type, "CEX", "defi", "tradfi", etc. repo link in comments.
0:18

open-sourced the KOL pricing tool i built for Minara AI growth. paste an X handle, get back in 5 seconds: - tier (trader / NFT / builder / influencer / mass + tool-builder overlay) - cash range + ROI per collab type - claude-drafted DM that quotes their actual recent tweets It's a self-hosted vue app that runs locally on your PC. you will need to fill in your own X & LLM API keys. And all rating records stay on your PC as well. also you can change the KOL type based on your product type, "CEX", "defi", "tradfi", etc. repo link in comments.

antoniayly

17,923 просмотров • 2 месяцев назад