Available today on SambaNova Cloud, developers now have access to some of the best open-source models in the Qwen 2.5 series: Qwen 72B and 32B-Coder. Thanks to the efficiency of SambaNova RDU chips, the Qwen 2.5 Coder model is capable of running over 5X faster than any GPU provider.
To make it easier for developers to start utilizing during day to day development, we have partnered with Continue.dev to make it easier to integrate these models and experience fast inference response times. To get started, head over to SambaNova Cloud, get your API key and integrate it into your IDE. To read more about it, check out Continue’s blog post.
Moreover, developers can also start to utilize these models when developing Coding Agents as these state-of-art-models are fully capable of writing, editing, and optimizing code autonomously. See the demo of Qwen 2.5 Coder building the website in a fraction of the time it would take to run on GPUs. Try it now.
Prompt: Write code in a single HTML: Capture the click event, place a random number of emojis at the click position, and add gravity and collision effects to each emoji.
Results: Qwen 32B Coder on SambaNova (left) | ChatGPT (right)
Vertical Specific AI models are increasingly becoming more important for AI engineers due to improved speed and accuracy they bring. This is especially true with Coding Models as highlighted by the advancements of the Qwen team and their 32B-Coder. This model performs better than GPT-4o across various coding focused benchmarks and will be a great asset for developers.
SambaNova Cloud is available as a service for developers to easily integrate the best open source models with the fastest inference speeds. These speeds are powered by our state of the art AI Chip, the SN40L. Whether you are building AI agents or chatbots, fast inference speeds are a MUST for your end users to have a seamless real-time experience. Get started in minutes with these models and more on SambaNova Cloud for free today.