News

cloudmagazin
cloudmagazin.com > en > 07/16/2026 > inkling-what-the-new-open-weights-model-can-do

Inkling: What the new Open-Weights model can do

10+ hour, 39+ min ago  (505+ words) Related:When GPUs Eat the SaaS Budget / AI Campuses in DE: Separate Live Build and Planning What is Inkling? Inkling is an open-weights model from Thinking Machines Lab. The company publishes the trained model weights under Apache 2.0 so teams can…...

cloudmagazin
cloudmagazin.com > 06/03/2026 > fp8-fp4-und-vllm-wie-quantisierung-die-gpu-kosten-der-ki

**Reducing GPU Costs for AI Inference: FP8, FP4, and vLLM**

1+ mon, 1+ week ago  (699+ words) A production language model doesn’t burn its GPU hours during one-time training-it does so with every single request. When a service scales from hundreds to hundreds of thousands of daily calls, inference becomes the largest line item on the cloud…...