Moonshotai Kimi K2 Instruct needs about 622.1 GB of memory at Q4_K_M (a 620.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 218.4 GB (TQ1_0) to 2053.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Moonshotai Kimi K2 Instruct is a 1030B-parameter Kimi model in GGUF format, quantized by terribleplan. Its trained context length is 128K tokens. The repository has 7 quant files, from 218.4 GB (TQ1_0) to 2053.2 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 218.4 GB (5 parts) | 220.0 GB | Too big | Get file → | |
| Q2_K | 372.9 GB (8 parts) | 374.5 GB | Too big | Get file → | |
| Q3_K_L | 530.5 GB (11 parts) | 532.1 GB | Too big | Get file → | |
| Q4_K_M | 620.6 GB (13 parts) | 622.1 GB | Too big | Get file → | |
| Q6_K | 842.6 GB (18 parts) | 844.2 GB | Too big | Get file → | |
| Q8_0 | 1091.1 GB (23 parts) | 1092.6 GB | Too big | Get file → | |
| BF16 | 2053.2 GB (45 parts) | 2054.7 GB | Too big | Get file → |
What GPU do you need for Moonshotai Kimi K2 Instruct?
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 Moonshotai Kimi K2 Instruct quant should you choose?
Q4_K_M is the usual starting point for Moonshotai Kimi K2 Instruct: it balances file size and quality well. Here it is a 620.6 GB file.
The Q8_0 file is 1091.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is TQ1_0 at 218.4 GB, with the quality trade-offs that come with fewer bits. 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 Moonshotai Kimi K2 Instruct
How much VRAM does Moonshotai Kimi K2 Instruct need?
About 622.1 GB at Q4_K_M with an 8K context window. That is the 620.6 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 Moonshotai Kimi K2 Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 220.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Moonshotai Kimi K2 Instruct GGUF?
It depends on the quant: TQ1_0 is 218.4 GB, Q2_K is 372.9 GB, Q3_K_L is 530.5 GB, Q4_K_M is 620.6 GB, Q6_K is 842.6 GB, Q8_0 is 1091.1 GB and 1 more.
What context length does Moonshotai Kimi K2 Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Moonshotai Kimi K2 Instruct GGUF?
The files are on Hugging Face in the terribleplan/moonshotai_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 Moonshotai 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.