Thinking Machines Inkling lands on Dell Enterprise Hub

Thinking Machines’ Inkling NVFP4-quantized is now available on Dell Enterprise Hub. A 975B-parameter (41B active) multimodal Mixture-of-Experts model that takes text, image, and audio inputs and generates text for conversational, agentic, and coding workloads. Deploy it on-prem with SGLang on XE9680 (8×H200) and XE9780 (4 and 8×B300).

Deploy Inkling-NVFP4 →