Hello, and welcome to this week’s changelog update! Let’s dive into what’s new:
-
New One-Click AI Models: QwQ 32B, R1 1776 Distill Llama 70B, and more
You can now deploy the latest QwQ 32B from Qwen, R1 1776 Distill Llama 70B from Perplexity, and Coder and Math-specific models based on Qwen 2.5 with one click from the catalog.
-
2x, 4x, and 8x H100 GPU Instances available on request
We now offer 2x, 4x, and 8x H100 GPU instances. These new instances allow you to right-size GPU acceleration for your workloads on H100.
-
Control panel: New instance and regions selector
We’ve simplified instance and region selection for services under a unified section. This change eliminates the need to adjust these settings separately.