BLAST RADIUS

Open-weight & owned stack · Training tuning

Nous Research Publishes Fine-Tuned Inkling Artifacts

Nov 9, 2026

Nous Research published weights and training pairs from a 1,202-step fine-tuning of Thinking Machines Lab’s Inkling model.

Read the original at allblogthings.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

AI-Built Adobe Clones Gain Rapid Open-Source AdoptionNov 9Asahi Linux Switches Code License From MITNov 9Pinterest Deploys Fine-Tuned Qwen3 ModelNov 9Amazon Researchers Publish HOPE Expert Pruning MethodNov 9Researchers Demonstrate Training-Domain Fingerprinting Of LoRANov 9