Thinking Machines releases Inkling-Small, an open-weight model with 276B total and 12B active parameters, saying it "achieves comparable performance" to Inkling (Thinking Machines Lab)

Techmeme ·

Thinking Machines released Inkling-Small, a 276B-parameter open-weight MoE model with 12B active parameters and claimed Inkling-level performance.

Categories: Model Releases, OSS & Tools

Excerpt

<a href="https://thinkingmachines.ai/news/inkling-small/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260730/i42.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260730/p42#a260730p42" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="https://thinkingmachines.ai/">Thinking Machines Lab</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://thinkingmachines.ai/news/inkling-small/">Thinking Machines releases Inkling-Small, an open-weight model with 276B total and 12B active parameters, saying it &ldquo;achieves comparable performance&rdquo; to Inkling</a></b></span>&nbsp; &mdash;&nbsp; Try on Tinker Model card Hugging Face&nbsp; &mdash;&nbsp; Today, we are releasing Inkling-Small, an efficient open-weights model &hellip; </p>

Read at source: https://www.techmeme.com/260730/p42#a260730p42