# Moonshot AI releases Kimi K3, a 2.8T-parameter MoE model

> The open-weights multimodal model leans into coding and agentic tasks, extending Moonshot's Kimi line into a new scale bracket.

Published by The Open Weights on Jun 13, 2026. Canonical: https://theopenweights.com/news/kimi-k3-xyt3

## Key facts

- Company: Moonshot AI
- Model: Kimi K3
- Version: K3
- Category: Text / LLM
- Modalities: Text / LLM, Vision-Language, Reasoning
- License: Other (Open weights, commercial use allowed)
- Parameters: 2800B (mixture of experts)
- Context window: 1.0M tokens
- Architecture: KimiK3ForConditionalGeneration
- Precision: INT8
- Weights size: 2837.1 GB
- Significance: major
- Published: 2026-06-13
- Last verified: 2026-09-23
- Hugging Face: https://huggingface.co/moonshotai/Kimi-K3
- Canonical URL: https://theopenweights.com/news/kimi-k3-xyt3

Moonshot AI has published Kimi K3, the latest entry in its Kimi family, releasing the weights openly on [Hugging Face](https://huggingface.co/moonshotai/Kimi-K3). The model is a mixture-of-experts (MoE) system with roughly 2.8 trillion total parameters, positioning it among the largest openly distributed models to date.

K3 is described as multimodal, handling both text and vision inputs, with an emphasis on reasoning. Moonshot points to coding and agentic workloads as areas of particular strength — the kinds of tasks that increasingly define how frontier-scale models are judged, from writing and debugging software to orchestrating multi-step tool use.

## Why it matters

Openly released weights at this scale remain rare. Most models in the multi-trillion-parameter range stay behind APIs, so a downloadable MoE of this size gives researchers and companies a chance to study and self-host capabilities that are usually gated.

- **Architecture:** mixture-of-experts, ~2.8T total parameters
- **Modalities:** text and vision, with a reasoning focus
- **Focus areas:** coding and agentic performance
- **Access:** weights available on Hugging Face under a custom license

A few practical details, including context length and the exact license terms, aren't spelled out in the release record, so teams evaluating K3 for production should check the [model card](https://huggingface.co/moonshotai/Kimi-K3) directly. As with earlier Kimi releases, the real test will be independent benchmarking and how the model holds up on long-horizon agentic tasks outside curated demos.

## Get the model

- [Hugging Face](https://huggingface.co/moonshotai/Kimi-K3)

## Sources

- [moonshotai/Kimi-K3](https://huggingface.co/moonshotai/Kimi-K3) — Hugging Face, Jun 13, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Moonshot AI releases Kimi K3, a 2.8T-parameter MoE model", The Open Weights, Jun 13, 2026, https://theopenweights.com/news/kimi-k3-xyt3