Inkling – Open-Weights 975B Parameter LLM

Inkling, a 975-billion-parameter open-weights large language model with only 41 billion active parameters, is now available for fine-tuning, enabling developers to reduce computational costs while maintaining performance across text, image, and speech tasks. The model's efficient architecture cuts GPU memory needs by roughly 20 times, allowing deployment of a single model for multimodal tasks without swapping architectures.

Hacker News https://thinkingmachines.ai/inkling/ Inkling – Open-Weights 975B Parameter LLM Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated. A 975B parameter LLM with only 41B active parameters is now available for fine-tuning, enabling developers to potentially reduce the computational cost of customizing large models while maintaining their performance; this capability matters because it allows for more efficient domain adaptation without sacrificing the model's multimodal capabilities and tool usage. 975B-parameter open-weights model with only 41B active at inference, cutting GPU memory needs by ~20× while matching top-tier performance on code, math, and multimodal tasks. This lets you deploy a single model that handles text, images, and speech in production without swapping architectures, and fine-tune it on your own data for domain-specific workflows without hitting memory walls. Expect lower cloud costs and faster iteration, but watch for calibration drift if you push thinking-time too low.