Cerebras Deploys Trillion-Parameter AI Models(cerebras.ai)
349 points by gmays | 127 comments
Cerebras blog post explaining how trillion-parameter models like Kimi K3 are split across multiple WSE-3T wafers for pipelined, high-throughput inference.
#kimi-k3 on Hacker News
9 stories tagged kimi-k3, newest first.
Run Kimi K3 using 29 GB of RAM at 0.50 tok/s(github.com)
318 points by marcobambini | 152 comments
GitHub repository for waste, a dependency-free embeddable C inference engine that runs the 2.78-trillion-parameter Kimi K3 model by streaming weights from NVMe.
Kimi K3-256k(kimi.com)
469 points by monneyboi | 138 comments
Kimi Code documentation page describing available models (Kimi K3 and Kimi K2.7 Code), their model IDs, and how to switch between them in clients.
Kimi K3 Architecture Overview and Notes(sebastianraschka.com)
472 points by ModelForge | 101 comments
Sebastian Raschka's blog post with an architecture figure and notes on the Kimi K3 open-weight model, a 2.8T scaled-up version of Kimi Linear.
![Screenshot of github.com: Kimi-K3 Technical Report [pdf]](https://hn.urlbox.com/shots/renders/2026/7/27/25fa6302-639e-4963-8edf-f78a1d553706.jpg)
Kimi-K3 Technical Report [pdf](github.com)
344 points by vinhnx | 148 comments
GitHub-hosted PDF of Moonshot AI's technical report for Kimi K3, an open frontier large language model.
Kimi-K3 on HuggingFace(huggingface.co)
1294 points by nateb2022 | 508 comments
Hugging Face placeholder page for Moonshot AI's upcoming Kimi-K3 model, showing a release countdown to July 27, 2026 and a notify button.
Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA(fireworks.ai)
816 points by piotrgrabowski | 416 comments
Fireworks AI blog post claiming the Kimi K3 model is competitive with Fable and that combining Kimi K3 with Fable achieves state-of-the-art results.
The Kimi K3 Moment(stephen.bochinski.dev)
543 points by sbochins | 513 comments
Blog post by Stephen Bochinski arguing that Kimi K3 produces code comparable to Claude at a much lower cost.
Kimi K3, and what we can still learn from the pelican benchmark(simonwillison.net)
387 points by droidjj | 209 comments
Simon Willison blog post on Moonshot AI's 2.8-trillion-parameter Kimi K3 model, its benchmarks and pricing, and his pelican-on-a-bicycle test results.