LLMs ·

Kimi K3.1 Pro (2.8T) New

Parameters
2,780B (104.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
kimi-k3.1-pro
Released
2026-10

How to run it

Ollama

Ollama offers this only as a cloud model (it runs on Ollama’s servers, not your machine). No GGUF build was available yet, so to run it locally use the original weights with vLLM or SGLang.

Original weights · Hugging Face

Full-precision files from Moonshot AI, for fine-tuning, vLLM, Transformers.

huggingface.co/moonshotai/Kimi-K3.1-Pro (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run Kimi K3.1 Pro (2.8T)

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

Docker Model Runner

Handy if you already work in Docker.

Also good:

App Type Opens it as Systems Engine Start
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve moonshotai/Kimi-K3.1-Pro
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path moonshotai/Kimi-K3.1-Pro
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/moonshotai/Kimi-K3.1-Pro
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

KV cache: hybrid linear attention: about 1 in 4 layers keeps a latent (MLA) cache, read with sparse (DSA) attention; active parameters as published.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 1,112 GB 1,113 GB 1,114 GB All files (opens in a new tab)
Q3_K_M Low 1,362 GB 1,363 GB 1,364 GB All files (opens in a new tab)
Q4_K_M Good 1,696 GB 1,697 GB 1,697 GB All files (opens in a new tab)
Q5_K_M High 1,974 GB 1,975 GB 1,975 GB All files (opens in a new tab)
Q6_K High 2,280 GB 2,281 GB 2,281 GB All files (opens in a new tab)
Q8_0 Very high 2,947 GB 2,948 GB 2,948 GB All files (opens in a new tab)
F16 Full 5,560 GB 5,561 GB 5,562 GB Original weights (opens in a new tab)

Best hardware for Kimi K3.1 Pro (2.8T)

None. No single GPU or device in our catalog runs this model on its own; it needs several GPUs working together.

Check it on your own hardware

Run it on a cluster

Devices that can’t run Kimi K3.1 Pro (2.8T) alone can run it together. These example clusters do:

Try it with your own devices

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?