hunyuan npu models needs about 5.9 GB of memory at IQ4_NL (a 4.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 4.4 GB (Q4_0) to 7.7 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
hunyuan npu models is a 12.8B-parameter Hunyuan model in GGUF format, quantized by JiangFeng12. Its trained context length is 125K tokens. The repository has 10 quant files, from 4.4 GB (Q4_0) to 7.7 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 4.4 GB | 5.4 GB | Fits | Get file → | |
| IQ4_NL | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.5 GB | Fits | Get file → | |
| IQ4_NL | 4.9 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 4.9 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 4.9 GB | 5.9 GB | Fits | Get file → | |
| IQ4_NL | 4.9 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 4.9 GB | 5.9 GB | Fits | Get file → | |
| IQ4_NL | 7.7 GB | 8.7 GB | Too big | Get file → | |
| Q4_0 | 7.7 GB | 8.7 GB | Too big | Get file → |
What GPU do you need for hunyuan npu models?
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: the best quant that fits is IQ4_NL (4.9 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_NL (4.9 GB file, about 5.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (7.7 GB file, about 8.7 GB in use).
Which hunyuan npu models quant should you choose?
IQ4_NL (4.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 4.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about hunyuan npu models
How much VRAM does hunyuan npu models need?
About 5.9 GB at IQ4_NL with an 8K context window. That is the 4.9 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 hunyuan npu models on an 8 GB GPU?
Yes, with IQ4_NL: the 4.9 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of hunyuan npu models GGUF?
It depends on the quant: Q4_0 is 4.4 GB, IQ4_NL is 4.5 GB, Q4_0 is 4.5 GB, IQ4_NL is 4.9 GB, IQ4_NL is 4.9 GB, Q4_0 is 4.9 GB and 4 more.
What context length does hunyuan npu models support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download hunyuan npu models GGUF?
The files are on Hugging Face in the JiangFeng12/hunyuan-npu-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does hunyuan npu models 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.