Kimi K3 needs about 1730.2 GB of memory at MXFP4_MOE (a 1561.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 674.0 GB.
Kimi K3 is a 2780B-parameter Kimi model in GGUF format, quantized by hudabey. Its trained context length is 1024K tokens. The repository has 1 quant file, from 1561.2 GB (MXFP4_MOE) to 1561.2 GB (MXFP4_MOE).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 1561.2 GB (34 parts) | 1730.2 GB | Too big | Get file → |
What GPU do you need for Kimi K3?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Kimi K3 quant should you choose?
MXFP4_MOE (1561.2 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kimi K3
How much VRAM does Kimi K3 need?
About 1730.2 GB at MXFP4_MOE with an 8K context window. That is the 1561.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Kimi K3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 1730.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kimi K3 GGUF?
It depends on the quant: MXFP4_MOE is 1561.2 GB.
What context length does Kimi K3 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 168.5 GB at 8K and 674.0 GB at 32K.
Where can I download Kimi K3 GGUF?
The files are on Hugging Face in the hudabey/Kimi-K3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Kimi K3 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.