Inkling: Our Open-Weights Model

	Inkling: Our Open-Weights Model(thinkingmachines.ai)
	1209 points by vimarsh6739 56 days ago \| 289 comments
	tl;dr: Inkling is a new open-weights Mixture-of-Experts model (975B total, 41B active) with a 1M-token context, native multimodality (text, image, audio), and controllable thinking effort, pretrained on 45T tokens. It's positioned not as a frontier leader but as a strong, balanced base for fine-tuning, benchmarking competitively against open-weights peers like Kimi K2.6 and GLM 5.2, and is available today on Tinker and Hugging Face. A smaller 276B/12B-active variant, Inkling-Small, is previewed with comparable performance on many benchmarks.
	HN Discussion: ↑Excitement about the multimodal and audio capabilities in an open-weights model ↑Appreciation for an American open-weights alternative to Chinese models like DeepSeek ↑The open base model plus Tinker fine-tuning is a strong business strategy ↑Real-world testing suggests the model outperforms what benchmarks indicate ~Model has uneven strengths, notably weaker at coding but good at instruction following