# Kimi-K3.1-Pro

> Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series.

- **Organisation:** moonshotai
- **Category:** Vision-Language Models, Chat & Text Generation
- **Parameters:** 2.78T
- **Context length:** 1,048,576 tokens
- **Licence:** kimi-k3.1-pro (Check licence)
- **Released:** 2026-11-02
- **Hugging Face:** 68K downloads (30 days), 2.4K likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 946.56 |
| Q3_K_M | 1381.55 |
| Q4_K_M | 1700.99 |
| Q5_K_M | 1986.44 |
| Q6_K | 2292.29 |
| Q8_0 | 2941.37 |
| F16 | 5490.09 |

## Runs with

- [Transformers](https://github.com/huggingface/transformers)

## Benchmarks

- GPQA Diamond: 94.2% (self-reported, rank 2/104)
- Humanity's Last Exam: 51.1% (self-reported, rank 7/63)
- MMMU-Pro: 84.1% (self-reported, rank 1/25)

## About

Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a 1-million-token context window, Kimi K3.1 Pro delivers substantial improvements in coding, 3D creation, financial research, factual accuracy, and other agentic capabilities.

Architecture Mixture-of-Experts (MoE) Total Parameters 2.8T Activated Parameters 104B Number of Layers 93 Number of Dense Layers 1 Attention-Layer Composition 69 KDA + 24 Gated DSA * Attention Hidden Dimension 7168 Number of Attention Heads 96 DSA Index Head Dimension 128 DSA Index Number of Heads 32 DSA Index Top-K 2048 Latent MoE Dimension 3584 MoE Hidden Dimension (per Expert) 3072 Number of Experts 896 Selected Experts per Token 16 Number of Shared Experts 2 Vocabulary Size 160K Context Length 1048576 Attention Mechanism KDA & Gated DSA Activation Function SiTU-GLU Vision Encoder MoonViT-V2 Parameters of Vision Encoder 401M Quantization MXFP4 weights / MXFP8 activations (quantization-aware training) Modality Text, Image

* Compared with Kimi K3, we replace the full-attention Gated MLA layers with Gated DeepSeek Sparse Attention (Gated DSA) layers for more efficient long-context modeling.

## Alternatives

- [moonshotai/Kimi-K3](https://selfhost.directory/models/moonshotai/kimi-k3) (2.78T, kimi-k3, ≈1700.88 GB at Q4): Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window.
- [meituan-longcat/LongCat-2.5](https://selfhost.directory/models/meituan-longcat/longcat-2.5) (1.78T, MIT, ≈1069.87 GB at Q4): LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token.
- [thinkingmachines/Inkling](https://selfhost.directory/models/thinkingmachines/inkling) (952B (18.1B active), Apache 2.0, ≈567.17 GB at Q4): Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.
- [moonshotai/Kimi-K2.7-Code](https://selfhost.directory/models/moonshotai/kimi-k2.7-code) (1.03T (33.3B active), modified-mit, ≈632.16 GB at Q4): Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by…
- [deepseek-ai/DeepSeek-V4.1-Flash](https://selfhost.directory/models/deepseek-ai/deepseek-v4.1-flash) (763B (188B active), MIT, ≈453.59 GB at Q4): We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.
- [moonshotai/Kimi-K2.6](https://selfhost.directory/models/moonshotai/kimi-k2.6) (1.03T (33.3B active), modified-mit, ≈632.16 GB at Q4): Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

More: https://selfhost.directory/models/moonshotai/kimi-k3.1-pro/alternatives

## Similar size

- [moonshotai/Kimi-K3](https://selfhost.directory/models/moonshotai/kimi-k3) (2.78T)

## FAQ

**How much VRAM does Kimi-K3.1-Pro need?**
About 1701 GB at Q4_K_M with an 8K context. Q8_0 needs about 2941 GB and full precision about 5490 GB. Longer contexts need more memory for the KV cache.

**Can Kimi-K3.1-Pro run on a consumer GPU?**
Not comfortably on a single one: it needs about 1701 GB at Q4. Split it over several GPUs, use a large unified-memory machine, or offload part of it to system RAM.

**Can I use Kimi-K3.1-Pro commercially?**
Unclear. It is released under kimi-k3.1-pro. Custom licence: read the model card before using it commercially. Check the licence on the model card before using it in a product.

**What is the context length of Kimi-K3.1-Pro?**
1,048,576 tokens (1M). The full window needs far more memory than an 8K context.

**How do I run Kimi-K3.1-Pro locally?**
It runs with Transformers. Each has copy-paste examples in its docs.

## Links

- huggingface: https://huggingface.co/moonshotai/Kimi-K3.1-Pro
- homepage: https://openai.com/index/gpt-6-astra/

---
Source: https://selfhost.directory/models/moonshotai/kimi-k3.1-pro