Introducing Ollama fully Integrated into VSCode with CodeGPT Now you can download open-source models from ollama with a single click and install them as code assistants in VSCode. In this case, I download the qwen2:0.5b (Qwen) model in under a minute, and it becomes fully functional with just one... click. The era of locally running code assistants has begun! 🚀show more

@ollama @Alibaba_Qwen Possible? Just to clarify I'd want to direct the requests to another machine that I control, one with more GPU firepower

@dani_avila7 @Alibaba_Qwen Yes! Very possible. We do this at times to test on multiple NVDA A100s.

@ollama @Alibaba_Qwen Continue is awesome! 👏 We know the founder and they've done an incredible job. We offer a variety of features you might want to check out... CodeGPT is free :)

@ollama @Alibaba_Qwen Can't wait to try this!! Thanks @dani_avila7

@ollama @Alibaba_Qwen Okay, but what about autocomplete?

@ollama @Alibaba_Qwen I'm curious about Qwen's potential.

@ollama @Alibaba_Qwen Qwen2 is really good! Check out this comparison between the Qwen2:72B-instruct model and the Llama3-70B-Instruct model

@ollama @Alibaba_Qwen Any tips on how to make ollama faster all the models run super slow on my machine.

@ollama @Alibaba_Qwen What type of computer do you have???