QwQ 32B - the AI model that changes everything
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
It turns out one bad day really can change everything
David Pakman Show
67.2k views
THIS WILL CHANGE EVERYTHING
Timcast
78.3k views
This 100% uncensored AI model is insane… let’s run it
David Ondrej
49.6k views
Everything is great other than all of this stuff
David Pakman Show
17.8k views
THIS CHANGES EVERYTHING
Timcast IRL
44.2k views
The Epstein Docs That Could Change Everything
Philip DeFranco
386.3k views
The Banking Trick No One Is Explaining (This Changes Everything)
Minority Mindset
54.7k views
This 100% minimal AI Agent can do anything… just watch
David Ondrej
28.3k views
THIS COULD CHANGE EVERYTHING
Timcast
75.4k views
Everything needs to change
Theo - t3․gg
133.3k views
Top Comments (10)
Why are you running it locally at first and then showing it with OpenRouter? Why not doing the same in Cursor with the local Ollama server?
The default "ollama run qwq:32b" command for ollama will pull the Q4 model - which is about 20GB - (32b-q4_K_M). The largest ollama QWQ-32b model on the ollama site is 32b-fp16 - which is 66GB - to pull/run that you need to run "ollama run qwq:32b-fp16".
🔥 Try INFINITE THINKING in Vectal: https://www.vectal.ai/ 🚀 Wanna start a business with AI Agents? Go here: https://www.skool.com/new-society
Mate one day you need to do a video about hosting the saas....building is easy...hosting is very costly sometimes, we(the ones that just started) need a video to explain hosting.
David is crying now that manu's is on the doors... i hope your startup will not sink with this fast ai development!
How to use qwq in cursor only local?
Always keeping me up to date on new AI advancements, GG. Wouldn't be surprised if you had a Manus AI video up soon, general agent that just released for testing within the last day or so.
This will be. Implemented into my project thank you for the video
How can we setup mcp in cursor on windows 😢
may i ask why we have to download the qwin 32b locally if we are going to use it through open router on curser?
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
Why are you running it locally at first and then showing it with OpenRouter? Why not doing the same in Cursor with the local Ollama server?
The default "ollama run qwq:32b" command for ollama will pull the Q4 model - which is about 20GB - (32b-q4_K_M). The largest ollama QWQ-32b model on the ollama site is 32b-fp16 - which is 66GB - to pull/run that you need to run "ollama run qwq:32b-fp16".
🔥 Try INFINITE THINKING in Vectal: https://www.vectal.ai/ 🚀 Wanna start a business with AI Agents? Go here: https://www.skool.com/new-society
Mate one day you need to do a video about hosting the saas....building is easy...hosting is very costly sometimes, we(the ones that just started) need a video to explain hosting.
David is crying now that manu's is on the doors... i hope your startup will not sink with this fast ai development!
How to use qwq in cursor only local?
Always keeping me up to date on new AI advancements, GG. Wouldn't be surprised if you had a Manus AI video up soon, general agent that just released for testing within the last day or so.
This will be. Implemented into my project thank you for the video
How can we setup mcp in cursor on windows 😢
may i ask why we have to download the qwin 32b locally if we are going to use it through open router on curser?