HY-MT1.5-1.8B needs about 2.2 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 20 quants, from 0.0 GB to 3.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
HY-MT1.5-1.8B – 1.8B parameter translation model
HY-MT1.5-1.8B is a 1.79B parameter translation model based on the hunyuan-dense architecture. It supports mutual translation across 33 languages and includes 5 ethnic and dialect variations. The model was generated with llama.cpp commit `9a6369bb6`.
Good at
- Multilingual translation
- Dialect support
- Contextual translation
Limits
- No vision support
- License not specified
- Large context requires 262144 tokens
Best for
- Translation tasks in 33 languages
- Low‑resource language support
- Mixed‑language documents
Who it’s for. Developers building translation services or chatbots that need multilingual coverage without large GPU memory. Researchers exploring translation models with moderate parameter size.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XXS | 0.8 GB | 1.9 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 1.9 GB | Fits | Get file → | |
| IQ3_M | 0.9 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.0 GB | Fits | Get file → | |
| IQ4_NL | 1.0 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.1 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 2.2 GB | Fits | Get file → | |
| Q4_1 | 1.1 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q5_0 | 1.3 GB | 2.4 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.4 GB | Fits | Get file → | |
| Q5_1 | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q6_K_M | 1.5 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 1.9 GB | 2.9 GB | Fits | Get file → | |
| BF16 | 2.7 GB | 3.7 GB | Fits | Get file → | |
| F16 | 2.7 GB | 3.7 GB | Fits | Get file → | |
| BF16 | 3.6 GB | 4.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.18 GB file, 2.2 GB memory at 8 k context) or Q3_K_M (0.94 GB file, 2 GB memory). For 4 GB VRAM, Q3_K_M is recommended. For higher precision, Q8_0 (1.91 GB file, 2.9 GB memory) fits 8 GB VRAM but not 4 GB.
What GPU do you need for HY-MT1.5-1.8B?
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 BF16 (2.7 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.6 GB file, about 4.6 GB in use).
Which HY-MT1.5-1.8B quant should you choose?
Q4_K_M is the usual starting point for HY-MT1.5-1.8B: it balances file size and quality well. Here it is a 1.2 GB file.
The Q8_0 file is 1.9 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 the first one in the table at 0.0 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-MT1.5-1.8B
How much VRAM does HY-MT1.5-1.8B need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.2 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-MT1.5-1.8B on an 8 GB GPU?
Yes, with BF16: the 3.6 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of HY-MT1.5-1.8B GGUF?
It depends on the quant: file is 0.0 GB, IQ3_XXS is 0.8 GB, IQ3_XS is 0.8 GB, Q3_K_S is 0.9 GB, IQ3_M is 0.9 GB, Q3_K_M is 0.9 GB and 14 more.
What context length does HY-MT1.5-1.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download HY-MT1.5-1.8B GGUF?
The files are on Hugging Face in the Mungert/HY-MT1.5-1.8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run HY-MT1.5-1.8B on 8 GB VRAM?
Yes, using Q4_K_M or Q3_K_M quants will fit within 8 GB VRAM with approximate memory usage of 2.2 GB or 2 GB at 8 k context.
What quant gives the best speed on a 4 GB VRAM machine?
Q3_K_M offers the smallest file size (0.94 GB) and lowest memory estimate (2 GB) for 4 GB VRAM.
Does the model support vision tasks?
No, the model has no vision capabilities.