# Moonshot publishes Kimi K3.1 Pro weights as tiny Qwen-based models win narrow tasks

Kimi K3.1 Pro is reported as a 2.8-trillion-parameter mixture-of-experts model with 104 billion active parameters and a 1M-token context, and an 800-million-parameter fine-tune of Qwen3.5 is claimed to beat far larger models at generating Bash commands.

- Published: 2026-11-10T06:14:13.273Z
- Canonical: https://polylog.news/ai/2026-11-10/moonshot-publishes-kimi-k3-1-pro-weights-as-tiny-qwen-based
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Hugging Face: dale-2b-GGUF](https://huggingface.co/manuelgscom/dale-2b-GGUF), [AI Weekly (French)](https://aiweekly.co/fr/alerts/moonshot-publie-les-poids-de-kimi-k31-pro-moe-28-t-avec-contexte-1-m-et-gated), [Braindetox](https://braindetox.kr/en/posts/kimi_k3_1_pro_weights_released.html), [BuildMVPFast](https://www.buildmvpfast.com/blog/kimi-k3-1-pro-open-model-coding-pricing-2026)

Moonshot AI has posted the weights of Kimi K3.1 Pro on Hugging Face. Reports put the model at 2.8 trillion total parameters, 104 billion active parameters, 896 experts and a 1,048,576-token context. The repository is about 1.56 terabytes. O…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-10/moonshot-publishes-kimi-k3-1-pro-weights-as-tiny-qwen-based (subscription information: https://polylog.news/pricing).