FactArticle
Inkling is Thinking Machines Lab's first general model: fully open-weight, 975B total parameters, natively multimodal, and available on Tinker, Hugging Face, and partner platforms.
Soumith Chintala describes Inkling as Thinking Machines' first general-purpose model, emphasizing its open weights, huge parameter count, and native multimodal support across major platforms. ✦ AI generated
Soumith Chintala · Latent Space · 2026-07-16 · original ↗
Soumith Chintala framed it as Thinking Machines' 'first general model,' stressing open weights, 975B parameters, native multimodality, and availability on Tinker, Hugging Face, and partners.
Read full article ↗excerpt · fair-use quotation
Around this claim
Extends · 4
Inkling debuts at 41 on the Intelligence Index, making it the leading U.S. open-weights release, ahead of Nemotron 3 Ultra (38), Gemma 4 31B (29), and gpt-oss-120b (24).Artificial Analysis · Latent Space · conf 70%Inkling is a clear step up from Nemotron Ultra and the new best American open model, though still a bit behind GLM 5.2 on agentic benchmarks and Kimi K2.6 on multimodal tasks.Nathan Lambert · Latent Space · conf 65%Inkling uses relative positional encoding / relative attention bias instead of RoPE, which multiple technical observers called one of the most novel large-scale architecture choices in the release.eliebakouch · Latent Space · conf 65%Inkling's benchmark results are not that great, effectively amounting to 'another Kimi-K2.6', behind all closed models and GLM-5.2, and possibly rushed out ahead of Kimi-K3 and DeepSeek-V4-GA.Scaling01 · Latent Space · conf 60%