Hy MT2 1.8B 1.25Bit needs about 1.5 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Fast‑thinking multilingual translation model
Hy MT2 1.8B 1.25Bit is a 1.8 B parameter model quantized to 1.25‑bit by AngelSlim. It supports translation among 33 languages and follows translation instructions in multiple languages. The model is released under the Apache‑2.0 license.
Good at
- Fast multilingual translation
- Instruction‑following translation
- On‑device deployment
Limits
- Requires ~1.5 GB VRAM at 8 k context
- Model size 440 MB after 1.25‑bit quantization
- No vision or audio capabilities
Best for
- Real‑world business translation
- Domain‑specific translation tasks
- Integrating translation into mobile apps
Who it’s for. Developers and companies that need efficient, on‑device multilingual translation. The model is suitable for applications requiring quick inference and low storage footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.5 GB | Fits | Get file → |
The only available GGUF file is 0.46 GB with a 1.5 GB VRAM estimate at 8 k context. For 8 GB VRAM systems, this file fits comfortably. If memory is tighter, consider using a higher‑bit quantization if available, but no other quants are listed.
What GPU do you need for Hy MT2 1.8B 1.25Bit?
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 (0.5 GB file, about 1.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy MT2 1.8B 1.25Bit
How much VRAM does Hy MT2 1.8B 1.25Bit need?
About 1.5 GB at its main file with an 8K context window. That is the 0.5 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 Hy MT2 1.8B 1.25Bit on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hy MT2 1.8B 1.25Bit GGUF?
It depends on the quant: file is 0.5 GB.
What context length does Hy MT2 1.8B 1.25Bit 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 MT2 1.8B 1.25Bit GGUF?
The files are on Hugging Face in the tencent/Hy-MT2-1.8B-1.25Bit-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 1.8B 1.25Bit 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 Hy MT2 1.8B 1.25Bit on 8 GB VRAM?
Yes, the model requires about 1.5 GB VRAM at 8 k context, so it fits easily on an 8 GB GPU.
Does the model support image or audio input?
No, the model is purely text‑based and does not handle vision or audio modalities.
What license does the model use?
The model is released under the Apache‑2.0 license.