Hy MT2 30B A3B Uncensored Heretic needs about 19.5 GB of memory at Q4_K_M (a 18.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 24.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
30B‑MoE multilingual translation model with reduced safety alignment
Hy MT2 30B A3B Uncensored Heretic is a 30.1B‑parameter Mixture‑of‑Experts model based on hy_v3 architecture. It supports 33 languages and is trained on a custom mixed‑language dataset. The model is released under Apache‑2.0 and is intended for research and safety studies.
Good at
- Multilingual translation
- Reasoning tasks
- Tool usage
Limits
- Reduced safety alignment; may generate harmful content
- No vision support
- Requires large VRAM for full precision
Best for
- Research on multilingual translation
- Safety and alignment testing
- Red‑team evaluation
Who it’s for. Researchers and developers who need a large multilingual translation model for experimentation. The model is not suitable for public or end‑user deployment due to its reduced safety alignment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 6.2 GB | 7.5 GB | Tight | Get file → | |
| IQ1_M | 6.9 GB | 8.2 GB | Too big | Get file → | |
| IQ2_XXS | 8.0 GB | 9.3 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 10.2 GB | Too big | Get file → | |
| IQ2_S | 9.0 GB | 10.3 GB | Too big | Get file → | |
| IQ2_M | 9.9 GB | 11.2 GB | Too big | Get file → | |
| Q2_K_S | 10.3 GB | 11.6 GB | Too big | Get file → | |
| Q2_K | 11.1 GB | 12.4 GB | Too big | Get file → | |
| IQ3_XXS | 11.6 GB | 13.0 GB | Too big | Get file → | |
| IQ3_XS | 12.4 GB | 13.7 GB | Too big | Get file → | |
| Q3_K_S | 13.1 GB | 14.4 GB | Too big | Get file → | |
| IQ3_S | 13.1 GB | 14.4 GB | Too big | Get file → | |
| IQ3_M | 13.3 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_M | 14.4 GB | 15.8 GB | Too big | Get file → | |
| Q3_K_L | 15.6 GB | 16.9 GB | Too big | Get file → | |
| IQ4_XS | 16.1 GB | 17.4 GB | Too big | Get file → | |
| Q4_0 | 17.1 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_S | 17.2 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_M | 18.2 GB | 19.5 GB | Too big | Get file → | |
| Q4_1 | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q5_K_S | 20.7 GB | 22.1 GB | Too big | Get file → | |
| Q5_K_M | 21.4 GB | 22.7 GB | Too big | Get file → | |
| Q6_K | 24.7 GB | 26.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.21 GB, 7.5 GB memory) or Q2_K (11.06 GB, 12.4 GB memory). For 16 GB VRAM, IQ3_M (13.26 GB, 14.6 GB memory) or Q4_K_M (18.24 GB, 19.5 GB memory) provide a balance of size and performance. Use the smallest quant that meets your memory budget.
What GPU do you need for Hy MT2 30B A3B Uncensored Heretic?
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: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_S (6.2 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K_S (10.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (14.4 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (21.4 GB file, about 22.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (24.7 GB file, about 26.0 GB in use).
Which Hy MT2 30B A3B Uncensored Heretic quant should you choose?
Q4_K_M is the usual starting point for Hy MT2 30B A3B Uncensored Heretic: it balances file size and quality well. Here it is a 18.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy MT2 30B A3B Uncensored Heretic
How much VRAM does Hy MT2 30B A3B Uncensored Heretic need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 18.2 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 Hy MT2 30B A3B Uncensored Heretic on an 8 GB GPU?
Yes, with IQ1_S: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hy MT2 30B A3B Uncensored Heretic GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 6.2 GB, IQ1_M is 6.9 GB, IQ2_XXS is 8.0 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.0 GB and 18 more.
What context length does Hy MT2 30B A3B Uncensored Heretic support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Hy MT2 30B A3B Uncensored Heretic GGUF?
The files are on Hugging Face in the mradermacher/Hy-MT2-30B-A3B-uncensored-heretic-i1-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 Hy MT2 30B A3B Uncensored Heretic 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.
Can I run this model on 8 GB VRAM?
Yes, using the IQ1_S or Q2_K quantizations, which require approximately 7.5 GB or 12.4 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model does not have vision capabilities.
Is this model safe for production use?
No, it has reduced safety alignment and is intended only for research and experimentation.