HU

Hunyuan MT 7B

HunyuanGGUF by imikeliuUpdated 2025-09-02
Download on Hugging Face
Parameters7.5B
Context256K
Layers32
Architecturehunyuan-dense
Smallest quant4.6 GB
Quick answer

Hunyuan MT 7B needs about 6.2 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Hunyuan MT 7B – 7B‑parameter translation model in GGUF format

Hunyuan MT 7B is a 7 billion‑parameter translation model converted to GGUF. It supports 33 languages, including five ethnic minority languages in China. The model is optimized for inference with llama.cpp.

Good at

  • High‑quality mutual translation among 33 languages
  • Efficient inference with Q4_K_M quantization
  • Large context support up to 262,144 tokens

Limits

  • No vision or multimodal support
  • License not specified
  • Requires at least 6.2 GB VRAM with Q4_K_M

Best for

  • Multilingual translation tasks
  • Language‑model fine‑tuning for translation
  • Rapid prototyping of translation pipelines

Who it’s for. Developers and researchers needing a compact, high‑performance translation model for 33 languages. Suitable for edge deployment where memory is limited but translation quality is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.6 GB 6.2 GB
Fits Get file →

The Q4_K_M quantized file is 4.62 GB and needs about 6.2 GB VRAM at 8 k context. For 8 GB VRAM systems, Q4_K_M is the only available quant. If more memory is available, consider higher‑precision quants if they exist.

What GPU do you need for Hunyuan MT 7B?

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: the best quant that fits is Q4_K_M (4.6 GB file, about 6.2 GB in use).

Which Hunyuan MT 7B quant should you choose?

Q4_K_M is the usual starting point for Hunyuan MT 7B: it balances file size and quality well. Here it is a 4.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturehunyuan-dense
Parameters7.5B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byimikeliu
FamilyHunyuan
Downloads (HF)6,009
Last updated2025-09-02

Frequently asked questions about Hunyuan MT 7B

How much VRAM does Hunyuan MT 7B need?

About 6.2 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Hunyuan MT 7B on an 8 GB GPU?

Yes, with Q4_K_M: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hunyuan MT 7B GGUF?

It depends on the quant: Q4_K_M is 4.6 GB.

What context length does Hunyuan MT 7B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Hunyuan MT 7B GGUF?

The files are on Hugging Face in the imikeliu/Hunyuan-MT-7B-Q4_K_M-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 Hunyuan MT 7B on 8 GB VRAM?

Yes, the Q4_K_M quant requires approximately 6.2 GB VRAM at 8 k context, fitting within an 8 GB budget.

Does the model support vision tasks?

No, the model is purely text translation and does not include vision capabilities.

What context length can I use?

The model was trained with 262,144 tokens, but practical inference is limited by VRAM; 8 k context is typical.

Other GGUFs of Hunyuan-MT-7B

Similar models

Browse all →

More from imikeliu

All by imikeliu →

More Hunyuan models

All Hunyuan →

Other small models

All small models →