Kimi K2 Thinking needs about 376.2 GB of memory at its main file (a 374.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 235.1 GB to 583.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Kimi K2 Thinking is a 1030B-parameter Kimi model in GGUF format, quantized by ubergarm. Its trained context length is 256K tokens. The repository has 8 quant files, from 235.1 GB to 583.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 235.1 GB (5 parts) | 236.7 GB | Too big | Get file → | |
| — | 290.1 GB (6 parts) | 291.6 GB | Too big | Get file → | |
| — | 353.5 GB (8 parts) | 355.1 GB | Too big | Get file → | |
| — | 374.6 GB (8 parts) | 376.2 GB | Too big | Get file → | |
| — | 416.9 GB (9 parts) | 418.5 GB | Too big | Get file → | |
| — | 493.3 GB (11 parts) | 494.9 GB | Too big | Get file → | |
| — | 520.8 GB (11 parts) | 522.4 GB | Too big | Get file → | |
| — | 583.7 GB (13 parts) | 585.3 GB | Too big | Get file → |
What GPU do you need for Kimi K2 Thinking?
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 K2 Thinking quant should you choose?
If memory is tight, the smallest file is the first one in the table at 235.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kimi K2 Thinking
How much VRAM does Kimi K2 Thinking need?
About 376.2 GB at its main file with an 8K context window. That is the 374.6 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 Thinking on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 236.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kimi K2 Thinking GGUF?
It depends on the quant: file is 235.1 GB, file is 290.1 GB, file is 353.5 GB, file is 374.6 GB, file is 416.9 GB, file is 493.3 GB and 2 more.
What context length does Kimi K2 Thinking support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Kimi K2 Thinking GGUF?
The files are on Hugging Face in the ubergarm/Kimi-K2-Thinking-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 Thinking 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.