Tencent Hy MT2 30B A3B 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 7 quants, from 11.1 GB (Q2_K) to 60.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Tencent Hy MT2 30B A3B – a multilingual translation model with 30B parameters
Tencent Hy MT2 30B A3B is a 30B‑parameter multilingual translation model based on the hy_v3 architecture. It supports translation among 33 languages and follows translation instructions in multiple languages. The model is a mixture of experts with 3B active parameters and was trained on 262,144 context tokens.
Good at
- Fast‑thinking multilingual translation
- Instruction‑following translation tasks
- High performance on real‑world business scenarios
Limits
- Requires a llama.cpp build that supports hy_v3
- No vision support
- Large VRAM/RAM needed for higher‑bit quantizations
Best for
- Translation of technical documents
- Real‑time subtitle translation
- Business‑grade multilingual communication
Who it’s for. Developers and researchers needing high‑quality translation across many languages. Suitable for integration into translation pipelines or on‑device inference with compatible llama.cpp builds.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 11.1 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_M | 14.4 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_M | 18.2 GB | 19.5 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 → | |
| Q8_0 | 32.0 GB | 33.3 GB | Too big | Get file → | |
| BF16 | 60.2 GB | 61.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 18.24 GB, estimated 19.5 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (21.37 GB, 22.7 GB memory). For 16 GB VRAM, Q6_K (24.71 GB, 26 GB memory). BF16 requires 61.5 GB memory and is not recommended for limited GPUs.
What GPU do you need for Tencent Hy MT2 30B A3B?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 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).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.0 GB file, about 33.3 GB in use).
Which Tencent Hy MT2 30B A3B quant should you choose?
Q4_K_M is the usual starting point for Tencent Hy MT2 30B A3B: it balances file size and quality well. Here it is a 18.2 GB file.
The Q8_0 file is 32.0 GB, about 1.8 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 Q2_K at 11.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Tencent Hy MT2 30B A3B
How much VRAM does Tencent Hy MT2 30B A3B 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 Tencent Hy MT2 30B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Tencent Hy MT2 30B A3B GGUF?
It depends on the quant: Q2_K is 11.1 GB, Q3_K_M is 14.4 GB, Q4_K_M is 18.2 GB, Q5_K_M is 21.4 GB, Q6_K is 24.7 GB, Q8_0 is 32.0 GB and 1 more.
What context length does Tencent Hy MT2 30B A3B 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 Tencent Hy MT2 30B A3B GGUF?
The files are on Hugging Face in the litigerking/Hy-MT2-30B-A3B-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 Tencent Hy MT2 30B A3B 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 this model on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 19.5 GB of memory at 8 k context. Ensure your llama.cpp build supports hy_v3.
Does this model support vision tasks?
No, the model is purely for translation and does not include vision capabilities.
What llama.cpp version is needed?
A build that supports the hy_v3 architecture is required; generic builds may fail with an unknown model architecture error.