higgs needs about 5.5 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 19 quants, from 2.7 GB (TQ1_0) to 23.1 GB (F32).
Higgs TTS 2, a 5.77B parameter audio generation model
Higgs TTS 2 is a 5.77B parameter model designed for expressive audio generation. It is available in multiple GGUF quantizations and supports 8k context length. The model is open‑source and can be run locally with llama.cpp.
Good at
- Expressive TTS generation
- Multilingual zero‑shot dialogue
- Automatic prosody adaptation
Limits
- No vision support
- Requires 8k context for full performance
- License is other
Best for
- Audio generation for apps
- Voice cloning demonstrations
- Multilingual TTS prototypes
Who it’s for. Developers building local TTS solutions who need a high‑quality, open‑source model. Researchers interested in audio generation and multimodal experiments may also use it.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| TQ2_0 | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 4.2 GB | Fits | Get file → | |
| IQ3_XXS | 3.6 GB | 4.5 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 5.3 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 → | |
| Q4_K_M | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_1 | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q5_0 | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q5_1 | 5.4 GB | 6.5 GB | Fits | Get file → | |
| Q6_K | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 6.9 GB | 8.2 GB | Too big | Get file → | |
| F16 | 11.5 GB | 13.4 GB | Too big | Get file → | |
| BF16 | 11.5 GB | 13.4 GB | Too big | Get file → | |
| F32 | 23.1 GB | 26.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q5_0 (5.07 GB, 6.2 GB memory) or Q4_1 (4.76 GB, 5.8 GB memory). For 12 GB VRAM, Q6_K (5.72 GB, 6.9 GB memory) or Q5_1 (5.38 GB, 6.5 GB memory) are suitable. Higher quants like Q8_0 provide better quality but need more memory.
What GPU do you need for higgs?
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 TQ2_0 (2.9 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.8 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (6.9 GB file, about 8.2 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (11.5 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (11.5 GB file, about 13.4 GB in use).
- 32 GB VRAM: the best quant that fits is F32 (23.1 GB file, about 26.4 GB in use).
Which higgs quant should you choose?
Q4_K_M is the usual starting point for higgs: it balances file size and quality well. Here it is a 4.5 GB file.
The Q8_0 file is 6.9 GB, about 1.6 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 2.7 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 higgs
How much VRAM does higgs need?
About 5.5 GB at Q4_K_M with an 8K context window. That is the 4.5 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 higgs on an 8 GB GPU?
Yes, with Q6_K: the 5.7 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of higgs GGUF?
It depends on the quant: TQ1_0 is 2.7 GB, TQ2_0 is 2.9 GB, Q2_K is 3.3 GB, IQ3_XXS is 3.6 GB, IQ3_S is 3.8 GB, Q3_K_M is 3.8 GB and 13 more.
Where can I download higgs GGUF?
The files are on Hugging Face in the calcuis/higgs-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 higgs 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.
Can I run Higgs TTS 2 on 8 GB VRAM?
Yes, use Q5_0 or Q4_1 quantizations, which estimate 6.2 GB or 5.8 GB memory at 8k context.
Does the model support multiple languages?
Yes, it can generate multilingual TTS in zero‑shot mode.
Is the model vision capable?
No, Higgs TTS 2 does not support vision inputs.