HU

Hunyuan A13B Instruct

HunyuanGGUF by bartowskiUpdated 2025-07-08
Download on Hugging Face
Parameters80.4B
Context256K
Layers32
Architecturehunyuan-moe
Smallest quant17.8 GB
Quick answer

Hunyuan A13B Instruct needs about 50.9 GB of memory at Q4_K_M (a 49.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 25 quants, from 17.8 GB (IQ1_M) to 85.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Hunyuan A13B Instruct – 80B total, 13B active, 256K context

Hunyuan A13B Instruct is a 80.4 billion‑parameter model with 13 billion active parameters. It supports a 262144‑token context window and is built on a mixture‑of‑experts architecture. The model is available in multiple GGUF quantizations for llama.cpp.

Good at

  • Long‑context reasoning
  • Efficient inference with MoE
  • Large‑scale text generation

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is other

Best for

  • Research on resource‑efficient LLMs
  • Developing agents with long context
  • Running on high‑end GPUs

Who it’s for. Researchers and developers who need a large‑scale model that can be run efficiently with a mixture‑of‑experts approach. The model is suitable for advanced reasoning tasks and long‑document processing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M17.8 GB 19.3 GB
Too big Get file →
IQ2_XXS19.7 GB 21.3 GB
Too big Get file →
IQ2_XS22.7 GB 24.2 GB
Too big Get file →
IQ2_S22.7 GB 24.3 GB
Too big Get file →
IQ2_M25.7 GB 27.3 GB
Too big Get file →
Q2_K29.0 GB 30.5 GB
Too big Get file →
Q2_K_L29.1 GB 30.7 GB
Too big Get file →
IQ3_XXS32.4 GB 34.0 GB
Too big Get file →
IQ3_XS33.7 GB 35.3 GB
Too big Get file →
Q3_K_S35.5 GB 37.1 GB
Too big Get file →
IQ3_M37.3 GB 38.8 GB
Too big Get file →
Q3_K_M37.3 GB 38.8 GB
Too big Get file →
Q3_K_L38.8 GB 40.3 GB
Too big Get file →
Q3_K_XL38.9 GB 40.5 GB
Too big Get file →
IQ4_XS43.5 GB 45.1 GB
Too big Get file →
IQ4_NL45.9 GB 47.5 GB
Too big Get file →
Q4_046.6 GB 48.2 GB
Too big Get file →
Q4_K_S47.5 GB 49.1 GB
Too big Get file →
Q4_K_M49.3 GB 50.9 GB
Too big Get file →
Q4_K_L49.4 GB 51.0 GB
Too big Get file →
Q4_150.7 GB (2 parts) 52.3 GB
Too big Get file →
Q5_K_S55.7 GB (2 parts) 57.3 GB
Too big Get file →
Q5_K_M57.6 GB (2 parts) 59.2 GB
Too big Get file →
Q6_K66.3 GB (2 parts) 67.9 GB
Too big Get file →
Q8_085.4 GB (3 parts) 87.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (17.75 GB file, ~19.3 GB memory). For 12 GB VRAM, IQ2_S (22.73 GB file, ~24.3 GB memory). For 24 GB VRAM, Q4_K_M (49.32 GB file, ~50.9 GB memory). Split shards are available for Q4_1, Q5_K_S, Q5_K_M, Q6_K, and Q8_0.

What GPU do you need for Hunyuan A13B Instruct?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (19.7 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K_L (29.1 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ4_NL (45.9 GB file, about 47.5 GB in use).

Which Hunyuan A13B Instruct quant should you choose?

Q4_K_M is the usual starting point for Hunyuan A13B Instruct: it balances file size and quality well. Here it is a 49.3 GB file.

The Q8_0 file is 85.4 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 IQ1_M at 17.8 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-moe
Parameters80.4B (approximate, mixture of experts)
Active parameters13B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyHunyuan
Licenseother
Downloads (HF)1,671
Last updated2025-07-08

Frequently asked questions about Hunyuan A13B Instruct

How much VRAM does Hunyuan A13B Instruct need?

About 50.9 GB at Q4_K_M with an 8K context window. That is the 49.3 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 A13B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Hunyuan A13B Instruct GGUF?

It depends on the quant: IQ1_M is 17.8 GB, IQ2_XXS is 19.7 GB, IQ2_XS is 22.7 GB, IQ2_S is 22.7 GB, IQ2_M is 25.7 GB, Q2_K is 29.0 GB and 19 more.

What context length does Hunyuan A13B Instruct 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 A13B Instruct GGUF?

The files are on Hugging Face in the bartowski/tencent_Hunyuan-A13B-Instruct-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 Hunyuan A13B Instruct 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 Hunyuan A13B Instruct on 8 GB VRAM?

Yes, the IQ1_M quant requires about 19.3 GB memory at 8k context, which is close to 8 GB VRAM but may need swapping or lower context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports a 262144‑token context window.

Other GGUFs of Hunyuan-A13B-Instruct

Similar models

Browse all →

More from bartowski

All by bartowski →

More Hunyuan models

All Hunyuan →

Other large models

All large models →