Kimi K2 Instruct needs about 349.7 GB of memory at its main file (a 311.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 1.5 GB (Q8_0) to 595.3 GB.
Kimi K2 Instruct is a 1030B-parameter Kimi model in GGUF format, quantized by ubergarm. Its trained context length is 128K tokens. The repository has 8 quant files, from 1.5 GB (Q8_0) to 595.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.5 GB | 2.2 GB | Fits | Get file → | |
| — | 235.6 GB (5 parts) | 264.3 GB | Too big | Get file → | |
| — | 251.4 GB (6 parts) | 282.1 GB | Too big | Get file → | |
| — | 311.7 GB (7 parts) | 349.7 GB | Too big | Get file → | |
| — | 354.0 GB (8 parts) | 397.0 GB | Too big | Get file → | |
| — | 375.2 GB (8 parts) | 420.7 GB | Too big | Get file → | |
| — | 462.7 GB (10 parts) | 518.7 GB | Too big | Get file → | |
| — | 595.3 GB (13 parts) | 667.2 GB | Too big | Get file → |
What GPU do you need for Kimi K2 Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
Which Kimi K2 Instruct quant should you choose?
If memory is tight, the smallest file is Q8_0 at 1.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kimi K2 Instruct
How much VRAM does Kimi K2 Instruct need?
About 349.7 GB at its main file with an 8K context window. That is the 311.7 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 K2 Instruct on an 8 GB GPU?
Yes, with Q8_0: the 1.5 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kimi K2 Instruct GGUF?
It depends on the quant: Q8_0 is 1.5 GB, file is 235.6 GB, file is 251.4 GB, file is 311.7 GB, file is 354.0 GB, file is 375.2 GB and 2 more.
What context length does Kimi K2 Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download Kimi K2 Instruct GGUF?
The files are on Hugging Face in the ubergarm/Kimi-K2-Instruct-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 K2 Instruct 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.