HY

Hy-Mt2-7B

GGUFGGUF by unslothUpdated 2026-05-29
Download on Hugging Face
Parameters7.5B
Context256K
Layers32
Architecturehunyuan-dense
Smallest quant2.8 GB
Quick answer

Hy-Mt2-7B 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. This repository has 21 quants, from 2.8 GB (IQ2_M) to 15.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Hy-Mt2-7B: 7‑billion‑parameter multilingual translation model

Hy-Mt2-7B is a 7‑billion‑parameter model built on the hunyuan-dense architecture. 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

  • Multilingual translation
  • Instruction‑following translation
  • Real‑world business translation

Limits

  • No vision support
  • Requires 262,144 token context
  • Large VRAM for high‑quality quants

Best for

  • On‑device translation with low‑bit quants
  • Batch translation of long documents
  • Integrating into translation pipelines

Who it’s for. Developers building multilingual translation services or on‑device translation apps. Researchers needing a large‑scale translation model for evaluation or fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M2.8 GB 4.4 GB
Fits Get file →
Q2_K_XL3.1 GB 4.7 GB
Fits Get file →
IQ3_XXS3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.4 GB 5.0 GB
Fits Get file →
Q3_K_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_XL4.0 GB 5.5 GB
Fits Get file →
IQ4_XS4.2 GB 5.7 GB
Fits Get file →
Q4_04.4 GB 6.0 GB
Fits Get file →
IQ4_NL4.4 GB 6.0 GB
Fits Get file →
Q4_K_S4.4 GB 6.0 GB
Fits Get file →
Q4_K_M4.6 GB 6.2 GB
Fits Get file →
Q4_K_XL4.8 GB 6.4 GB
Fits Get file →
Q4_14.8 GB 6.4 GB
Fits Get file →
Q5_K_S5.2 GB 6.8 GB
Fits Get file →
Q5_K_M5.4 GB 6.9 GB
Fits Get file →
Q5_K_XL5.4 GB 7.0 GB
Fits Get file →
Q6_K6.2 GB 7.7 GB
Tight Get file →
Q6_K_XL6.8 GB 8.3 GB
Too big Get file →
Q8_08.0 GB 9.6 GB
Too big Get file →
Q8_K_XL9.6 GB 11.2 GB
Too big Get file →
BF1615.0 GB 16.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.62 GB file, ~6.2 GB VRAM at 8 k context). For 12 GB VRAM, Q5_K_M (5.37 GB file, ~6.9 GB VRAM) or Q6_K (6.16 GB file, ~7.7 GB VRAM). For 16 GB VRAM, Q6_K_XL (6.77 GB file, ~8.3 GB VRAM) or Q8_0 (7.98 GB file, ~9.6 GB VRAM).

What GPU do you need for Hy-Mt2-7B?

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: the best quant that fits is Q4_K_S (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_K_XL (9.6 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_K_XL (9.6 GB file, about 11.2 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.0 GB file, about 16.6 GB in use).

Which Hy-Mt2-7B quant should you choose?

Q4_K_M is the usual starting point for Hy-Mt2-7B: it balances file size and quality well. Here it is a 4.6 GB file.

The Q8_0 file is 8.0 GB, about 1.7 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 IQ2_M at 2.8 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

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

Source

Quantized byunsloth
Licenseapache-2.0
Downloads (HF)11,717
Last updated2026-05-29

Frequently asked questions about Hy-Mt2-7B

How much VRAM does Hy-Mt2-7B 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 Hy-Mt2-7B on an 8 GB GPU?

Yes, with Q6_K: the 6.2 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hy-Mt2-7B GGUF?

It depends on the quant: IQ2_M is 2.8 GB, Q2_K_XL is 3.1 GB, IQ3_XXS is 3.1 GB, Q3_K_S is 3.4 GB, Q3_K_M is 3.8 GB, Q3_K_XL is 4.0 GB and 15 more.

What context length does Hy-Mt2-7B 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 Hy-Mt2-7B GGUF?

The files are on Hugging Face in the unsloth/Hy-MT2-7B-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-Mt2-7B 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-Mt2-7B on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quants requires about 6–7 GB VRAM at 8 k context, which fits within 8 GB.

Does Hy-Mt2-7B support vision tasks?

No, the model does not include vision capabilities.

What license applies to Hy-Mt2-7B?

The model is released under the Apache‑2.0 license.

Other GGUFs of Hy-MT2-7B

Similar models

Browse all →

More from unsloth

All by unsloth →

Other small models

All small models →