HU

Hunyuan A13B Instruct

HunyuanGGUF by gabriellarsonUpdated 2025-07-08
Download on Hugging Face
Parameters80.4B
Context256K
Layers32
Architecturehunyuan-moe
Smallest quant16.3 GB
Quick answer

Hunyuan A13B Instruct needs about 50.4 GB of memory at Q4_K_M (a 48.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 16.3 GB (IQ1_S) to 160.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Hunyuan A13B Instruct – 13B active parameters, 256K context, MoE architecture

Hunyuan A13B Instruct is a Mixture-of-Experts LLM with 80.4B total parameters and 13B active parameters. It supports a 262144 token context window and is optimized for reasoning and tool use. The model is available in multiple GGUF quantizations.

Good at

  • Long‑context reasoning
  • Tool‑enabled tasks
  • Efficient inference with MoE

Limits

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

Best for

  • Research on long‑text generation
  • Agent‑style workflows
  • Resource‑constrained inference

Who it’s for. Researchers and developers needing high‑performance reasoning in a resource‑efficient model. Suitable for academic projects and cost‑sensitive deployments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S16.3 GB 17.9 GB
Too big Get file →
IQ1_M18.1 GB 19.7 GB
Too big Get file →
IQ2_XXS21.1 GB 22.7 GB
Too big Get file →
IQ2_XS23.6 GB 25.2 GB
Too big Get file →
IQ2_S23.8 GB 25.4 GB
Too big Get file →
IQ2_M26.3 GB 27.8 GB
Too big Get file →
Q2_K_S27.5 GB 29.0 GB
Too big Get file →
Q2_K29.4 GB 31.0 GB
Too big Get file →
IQ3_XXS31.0 GB 32.6 GB
Too big Get file →
IQ3_XS32.9 GB 34.5 GB
Too big Get file →
Q3_K_S34.8 GB 36.4 GB
Too big Get file →
IQ3_S34.8 GB 36.4 GB
Too big Get file →
IQ3_M35.3 GB 36.9 GB
Too big Get file →
Q3_K_M38.6 GB 40.1 GB
Too big Get file →
Q3_K_L41.7 GB 43.3 GB
Too big Get file →
IQ4_XS42.9 GB 44.5 GB
Too big Get file →
IQ4_NL45.4 GB 47.0 GB
Too big Get file →
Q4_045.6 GB 47.2 GB
Too big Get file →
Q4_K_S45.8 GB 47.4 GB
Too big Get file →
Q4_K_M48.8 GB 50.4 GB
Too big Get file →
Q5_K_S55.4 GB 56.9 GB
Too big Get file →
Q5_055.6 GB 57.2 GB
Too big Get file →
Q5_K_M57.1 GB 58.7 GB
Too big Get file →
Q6_K66.0 GB 67.6 GB
Too big Get file →
Q8_085.4 GB 87.0 GB
Too big Get file →
F16160.8 GB 162.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (16.3 GB file, 17.9 GB memory) or IQ1_M (18.12 GB file, 19.7 GB memory). For 16 GB VRAM, IQ2_XS (23.59 GB file, 25.2 GB memory) or Q2_K_S (27.47 GB file, 29 GB memory) are suitable. Higher‑quality quants like Q5_K_M require 57.12 GB file and 58.7 GB memory, so they need larger memory budgets.

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 (21.1 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K (29.4 GB file, about 31.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (45.8 GB file, about 47.4 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 48.8 GB file.

The Q8_0 file is 85.4 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 IQ1_S at 16.3 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 bygabriellarson
FamilyHunyuan
Licenseother
Downloads (HF)716
Last updated2025-07-08

Frequently asked questions about Hunyuan A13B Instruct

How much VRAM does Hunyuan A13B Instruct need?

About 50.4 GB at Q4_K_M with an 8K context window. That is the 48.8 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 17.9 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_S is 16.3 GB, IQ1_M is 18.1 GB, IQ2_XXS is 21.1 GB, IQ2_XS is 23.6 GB, IQ2_S is 23.8 GB, IQ2_M is 26.3 GB and 20 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 gabriellarson/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, with the IQ1_S or IQ1_M quant, which use about 17.9–19.7 GB memory at 8 k context.

Does the model support image input?

No, the model has no vision capabilities.

What context length does it support?

It supports up to 262144 tokens, equivalent to 256K context.

Other GGUFs of Hunyuan-A13B-Instruct

Similar models

Browse all →

More from gabriellarson

All by gabriellarson →

More Hunyuan models

All Hunyuan →

Other large models

All large models →