K3 Q4 needs about 2101.0 GB of memory at its main file (a 2098.7 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 7.3 GB.
K3 Q4 is a 3470B-parameter Kimi model in GGUF format, quantized by NomenAK. Its trained context length is 128K tokens. The repository has 1 quant file, from 2098.7 GB to 2098.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2098.7 GB (125 parts) | 2101.0 GB | Too big | Get file → |
What GPU do you need for K3 Q4?
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.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about K3 Q4
How much VRAM does K3 Q4 need?
About 2101.0 GB at its main file with an 8K context window. That is the 2098.7 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 K3 Q4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 2101.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of K3 Q4 GGUF?
It depends on the quant: file is 2098.7 GB.
What context length does K3 Q4 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.3 GB at 32K.
Where can I download K3 Q4 GGUF?
The files are on Hugging Face in the NomenAK/K3-Q4-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 K3 Q4 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.