K2 Think needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 14.8 GB (IQ3_M) to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
K2 Think is a 32.8B-parameter Think model in GGUF format, quantized by mmnga. Its trained context length is 128K tokens. The repository has 12 quant files, from 14.8 GB (IQ3_M) to 26.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 14.8 GB | 17.5 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 18.6 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_0 | 18.6 GB | 21.3 GB | Too big | Get file → | |
| IQ4_NL | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q4_K_S | 18.8 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_M | 19.9 GB | 22.5 GB | Too big | Get file → | |
| Q5_0 | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 23.3 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 29.5 GB | Too big | Get file → |
What GPU do you need for K2 Think?
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: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
Which K2 Think quant should you choose?
Q4_K_M is the usual starting point for K2 Think: it balances file size and quality well. Here it is a 19.9 GB file.
If memory is tight, the smallest file is IQ3_M at 14.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about K2 Think
How much VRAM does K2 Think need?
About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 K2 Think on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of K2 Think GGUF?
It depends on the quant: IQ3_M is 14.8 GB, Q3_K_M is 15.9 GB, Q3_K_L is 17.2 GB, IQ4_XS is 17.7 GB, Q4_0 is 18.6 GB, IQ4_NL is 18.7 GB and 6 more.
What context length does K2 Think support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download K2 Think GGUF?
The files are on Hugging Face in the mmnga/K2-Think-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 K2 Think use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.