HiggsTTS3 needs about 5.0 GB of memory at Q6_K (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.8 GB (Q4_K) to 9.3 GB.
HiggsTTS3 is a 4.65B-parameter Higgstts model in GGUF format, quantized by liampetti. The repository has 4 quant files, from 2.8 GB (Q4_K) to 9.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q6_K | 4.0 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 6.2 GB | Fits | Get file → | |
| — | 9.3 GB | 11.0 GB | Too big | Get file → |
What GPU do you need for HiggsTTS3?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.0 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 6.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 11.0 GB in use).
Which HiggsTTS3 quant should you choose?
Q6_K (4.0 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_K at 2.8 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 HiggsTTS3
How much VRAM does HiggsTTS3 need?
About 5.0 GB at Q6_K with an 8K context window. That is the 4.0 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 HiggsTTS3 on an 8 GB GPU?
Yes, with Q8_0: the 5.1 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of HiggsTTS3 GGUF?
It depends on the quant: Q4_K is 2.8 GB, Q6_K is 4.0 GB, Q8_0 is 5.1 GB, file is 9.3 GB.
Where can I download HiggsTTS3 GGUF?
The files are on Hugging Face in the liampetti/HiggsTTS3.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 HiggsTTS3 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.