The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestMoonshot AIK2 Thinking
Moonshot AIReasoning

Moonshot AI Releases Kimi-K2 Reasoning Model

The new Mixture-of-Experts model is designed for complex tasks but arrives in a custom compressed format with a restrictive license.

Nov 4, 2025
Major releaseOther
Kimi K2 Thinking

Chinese AI startup Moonshot AI has released Kimi-K2-Thinking, a new open-weight model aimed at tackling complex reasoning problems. The company describes the model as being designed for tasks that require “extended thinking,” positioning it as a specialized tool rather than a general-purpose chatbot. Architecturally, it is a Mixture-of-Experts (MoE) model, a design known for efficient scaling.

Uniquely, the model is not distributed in a standard format like SafeTensors. Instead, Moonshot has released the weights in a proprietary compressed format with a ‘.sbs’ extension. To use the model, developers must rely on the company's corresponding open-source inference framework, Kimi-Inference, which is designed to handle this specific format. The full model is available for download on Hugging Face.

Licensing and Limitations

The release is governed by the custom "Kimi-K2-Thinking License." While it permits academic research and general commercial use, it includes a significant restriction: the model cannot be used for any commercial purpose that directly competes with Moonshot AI's own products or services. This kind of non-compete clause places it in a category of controlled-use models, distinct from permissively licensed open-source software.

This release highlights a growing trend of companies making powerful models publicly available under specific, often restrictive, terms. For researchers, Kimi-K2-Thinking offers a new architecture to explore for advanced reasoning. However, the non-standard weight format and licensing terms present hurdles for broad commercial adoption and straightforward integration into the existing open-source ecosystem.

Sources

  • moonshotai/Kimi-K2-Thinking

    Hugging Face

    Visit
OlderBAAI Releases Emu3.5, an 'Any-to-Any' Multimodal ModelBAAI · Any-to-Any · last yearNewerBaidu Releases Open Vision-Language MoE ModelBaidu · Vision-Language · 12 months ago

Get the model

Hugging Face

Specs

Active params32B active
Context window262K tokens
ArchitectureDeepseekV3ForCausalLM
LicenseOTHER
Downloads47.4K
Likes1.7K

Can you run it?

Datacenter only — about 619.6 GB even as published.

  • COMPRESSED-TENSORS 4-bit (as published)

    8×H100 80 GB node

    619.6 GB
Your machine
GGUF builds
  • Mixture-of-experts: all 1030B parameters must be resident even though only 32B are active per token — active count affects speed, not memory.
  • Published weights are already quantized (COMPRESSED-TENSORS 4-bit); smaller builds are not assumed.
  • KV cache sized for 8,192 tokens of context; longer prompts need proportionally more.

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Text / LLMReasoning

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Moonshot AI

All Moonshot AI releases →
Kimi K3
Moonshot AI/Text / LLMDatacenter

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.

Jun 13, 2026
Kimi-K2.7-Code
Moonshot AI/CodeDatacenter

Moonshot AI Releases Kimi, a Multimodal Coding Model

The new Mixture-of-Experts model from the Chinese AI company can generate code while also understanding visual inputs, a rare combination in open models.

Jun 11, 2026
Moonshot AI/Vision-Language

Kimi K2.6 tops closed models in coding test

Moonshot AI's open-weights mixture-of-experts model reportedly outperformed Claude, GPT-5.5, and Gemini on a programming challenge.

May 3, 2026

More in Reasoning

All Reasoning →
DeepSeek-V4.1-Flash (1017)
DeepSeek/Vision-LanguageDatacenter

DeepSeek V4.1-Flash Adds Vision and Reasoning

The new MIT-licensed checkpoint folds image understanding and reasoning into DeepSeek's fast, mixture-of-experts Flash line.

Oct 17, 2026
Meta AI/Any-to-Any

Meta's Muse Spark Open Targets Agentic Coding

The new open-weight model pairs a million-token context window with Meta's bet on long-horizon coding agents.

Oct 15, 2026
Sage-A1.5
InternScience/Vision-LanguageConsumer GPU

Sage-A1.5 Brings Agentic Vision to Open MoE Models

InclusionAI's new mixture-of-experts model pairs visual understanding with tool use and code, aiming at agentic workflows under an Apache 2.0 license.

Oct 15, 2026