Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

💻 Agent mode just went local! Today, Mistral AI released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments It reached #1 on SWE-bench for open-source models, but more importantly in our real-world testing it has proven to be capable of navigating and autonomously...

continuedev's profile picture

Continue

7,463 subscribers

39,217 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieGamingBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

it's open source time, with a real leap for world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!
0:20

it's open source time, with a real leap for world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!

Victor M

34,323 Aufrufe • vor 1 Monat

It's fast!! Ollama now supports AMD graphics cards! All the features of Ollama can now be accelerated by AMD graphics cards in preview on Ollama for Linux and Windows. Try it 👇👇 *video is not edited.
0:18

It's fast!! Ollama now supports AMD graphics cards! All the features of Ollama can now be accelerated by AMD graphics cards in preview on Ollama for Linux and Windows. Try it 👇👇 *video is not edited.

ollama

108,069 Aufrufe • vor 2 Jahren

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun
0:11

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun

chiefofautism

340,773 Aufrufe • vor 4 Monaten

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.
0:10

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.

Skywork

1,398,646 Aufrufe • vor 10 Monaten

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

503,787 Aufrufe • vor 10 Monaten

Open UI Local 1 Click Launcher Open UI from wan deeee bee is a cool AI app that live-generates UIs. It's like Vercel's V0 but open source, and works with both ChatGPT & open source models via ollama Make sure to check out Matthew Berman's tutorial, and run it with 1 click.
0:17

Open UI Local 1 Click Launcher Open UI from wan deeee bee is a cool AI app that live-generates UIs. It's like Vercel's V0 but open source, and works with both ChatGPT & open source models via ollama Make sure to check out Matthew Berman's tutorial, and run it with 1 click.

cocktail peanut

53,965 Aufrufe • vor 2 Jahren

Wow Mistral has released its new model tailor-made for AI code assistants Codestral 25.01 (that's its name) is debuting at #1 on the LMsys copilot arena leaderboard 🔥 You can already use it for free in Continue (100% open-source) for VS Code
0:11

Wow Mistral has released its new model tailor-made for AI code assistants Codestral 25.01 (that's its name) is debuting at #1 on the LMsys copilot arena leaderboard 🔥 You can already use it for free in Continue (100% open-source) for VS Code

Paul Couvert

83,390 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 5 Monaten

We just released a demo for our game, Cursemark. It's an ARPG/Roguelike hybrid, with a lot of buildcraft and exploration in a dark fantasy world. Try it out and let us know what you think
0:15

We just released a demo for our game, Cursemark. It's an ARPG/Roguelike hybrid, with a lot of buildcraft and exploration in a dark fantasy world. Try it out and let us know what you think

ℭ𝔏𝔜𝔇𝔈 | ℭ𝔲𝔯𝔰𝔢𝔪𝔞𝔯𝔎

14,916 Aufrufe • vor 10 Monaten

The leading model runnable on a single cloud H100 GPU now fits on a single home GPU! 🔥 We've optimized Gemma 3 27B with QAT so you can run our best-in-class open model on your desktop RTX 3090 or similar. See how easy it is to try via ollama! 👇
0:16

The leading model runnable on a single cloud H100 GPU now fits on a single home GPU! 🔥 We've optimized Gemma 3 27B with QAT so you can run our best-in-class open model on your desktop RTX 3090 or similar. See how easy it is to try via ollama! 👇

Glenn Cameron Jr

81,427 Aufrufe • vor 1 Jahr

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.
0:15

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

Jafar Najafov

13,630 Aufrufe • vor 2 Monaten

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.
0:15

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

AlphaSignal AI

91,680 Aufrufe • vor 2 Monaten

We just shipped Gemini 2.5 Pro as an available model in Agent Mode. Try it out!
0:10

We just shipped Gemini 2.5 Pro as an available model in Agent Mode. Try it out!

Warp

43,691 Aufrufe • vor 1 Jahr

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇
0:19

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇

Krea

1,055,697 Aufrufe • vor 10 Monaten

Today Meta released "Code Llama", a large language model fine-tuned for coding tasks. It's publicly available and can be used for commercial use! It outperforms GPT 3.5 and you can even run it locally on your Macbook using Ollama.
0:11

Today Meta released "Code Llama", a large language model fine-tuned for coding tasks. It's publicly available and can be used for commercial use! It outperforms GPT 3.5 and you can even run it locally on your Macbook using Ollama.

Marcel Pociot 🧪

49,806 Aufrufe • vor 2 Jahren

Grok 4.1 Fast just dropped on the API 🔥 Until Dec 3rd: ✦ Grok 4.1 Fast = FREE on OpenRouter ✦All Agent Tools = 100 % FREE This is the agent model we've all been waiting for: ✦ Tool calling: #1 on Berkeley leaderboard ✦ Real-world: 100% on τ²-bench Telecom ✦ Context: 2M
0:14

Grok 4.1 Fast just dropped on the API 🔥 Until Dec 3rd: ✦ Grok 4.1 Fast = FREE on OpenRouter ✦All Agent Tools = 100 % FREE This is the agent model we've all been waiting for: ✦ Tool calling: #1 on Berkeley leaderboard ✦ Real-world: 100% on τ²-bench Telecom ✦ Context: 2M

tetsuo

3,209,868 Aufrufe • vor 7 Monaten

Our models run real time on a laptop 5090 at 100+ FPS. We're so excited for people to start playing with it.
0:10

Our models run real time on a laptop 5090 at 100+ FPS. We're so excited for people to start playing with it.

Louis Castricato @ lovecraftian horrors

137,685 Aufrufe • vor 10 Monaten

Just for fun, I tried training a 3D AI model. Made one that can tell cubes from other objects. Trained it on my laptop CPU with only 100 samples in 7 seconds Next time I’ll try something more advanced. #b3d #blender3d
0:11

Just for fun, I tried training a 3D AI model. Made one that can tell cubes from other objects. Trained it on my laptop CPU with only 100 samples in 7 seconds Next time I’ll try something more advanced. #b3d #blender3d

Casey Sheep

24,892 Aufrufe • vor 8 Monaten

India can’t be left behind in AI. कृत्रिम has accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!
0:12

India can’t be left behind in AI. कृत्रिम has accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!

Bhavish Aggarwal

379,427 Aufrufe • vor 1 Jahr

New Generation Model! 🚨 We're introducing the Mistral model to our expanding lineup of generation models. Mistral brings efficient performance and strong language understanding capabilities to our platform. Initial testing shows promising results in code comprehension and generation tasks, making it a valuable addition to development workflows. While we continue to optimize its implementation, early benchmarks demonstrate consistent and reliable outputs across various programming tasks.
0:17

New Generation Model! 🚨 We're introducing the Mistral model to our expanding lineup of generation models. Mistral brings efficient performance and strong language understanding capabilities to our platform. Initial testing shows promising results in code comprehension and generation tasks, making it a valuable addition to development workflows. While we continue to optimize its implementation, early benchmarks demonstrate consistent and reliable outputs across various programming tasks.

ALCHEMIST AI 🔮

16,418 Aufrufe • vor 1 Jahr