HY

Hy MT2 30B A3B

GGUFGGUF by GrahLnnUpdated 2026-05-23
Download on Hugging Face
Parameters30.1B
Context256K
Layers48
Architecturehy_v3
Smallest quant11.1 GB
Quick answer

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 3 quants, from 11.1 GB (Q2_K) to 18.2 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Hy MT2 30B A3B – 30.1B multilingual translation model

Hy MT2 30B A3B is a 30.1B parameter multilingual translation model with 3.0B active parameters in a mixture of experts architecture. It supports translation among 33 languages and follows translation instructions in multiple languages. The model is released in 4bit GGUF format.

Good at

  • Fast multilingual translation
  • Complex real‑world translation tasks
  • Instruction‑following translation

Limits

  • No vision support
  • Requires patched llama.cpp for hy_v3
  • License not specified

Best for

  • On‑device translation services
  • Multilingual content localization
  • Real‑time subtitle translation

Who it’s for. Developers building multilingual translation applications that need high accuracy and fast inference on local hardware. The model is suitable for teams that can patch llama.cpp to support the hy_v3 architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.1 GB 12.4 GB
Too big Get file →
Q3_K_M14.4 GB 15.8 GB
Too big Get file →
Q4_K_M18.2 GB 19.5 GB
Too big Get file →

For 8 k context, the Q2_K file uses about 12.4 GB of VRAM and is 11.06 GB on disk. Q3_K_M uses about 15.8 GB VRAM and is 14.45 GB on disk. Q4_K_M uses about 19.5 GB VRAM and is 18.24 GB on disk. Choose Q2_K for the lowest memory footprint, Q3_K_M for a balance, and Q4_K_M for the best quality within your budget.

What GPU do you need for 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 Q4_K_M (18.2 GB file, about 19.5 GB in use).

Which Hy MT2 30B A3B quant should you choose?

Q4_K_M is the usual starting point for Hy MT2 30B A3B: it balances file size and quality well. Here it is a 18.2 GB file.

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

Architecturehy_v3
Parameters30.1B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byGrahLnn
Downloads (HF)798
Last updated2026-05-23

Frequently asked questions about Hy MT2 30B A3B

How much VRAM does 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 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 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.

What context length does 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 Hy MT2 30B A3B GGUF?

The files are on Hugging Face in the GrahLnn/Hy-MT2-30B-A3B-4bit-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 MT2 30B A3B on 8 GB VRAM?

No. The smallest 4bit quantization requires at least 12.4 GB VRAM for 8 k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What patch is needed for llama.cpp?

A patch for HYV3ForCausalLM / model_type=hy_v3 is required to run the model.

Other GGUFs of Hy-MT2-30B-A3B

Similar models

Browse all →

Other medium models

All medium models →