MI

mirayu models

MirayuGGUF by thedemonsUpdated 2026-10-03
Download on Hugging Face
Parameters3.88B
Context40K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

mirayu models needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.5 GB (Q4_K_M) to 21.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

mirayu models is a 3.88B-parameter Mirayu model in GGUF format, quantized by thedemons. Its trained context length is 40K tokens. The repository has 10 quant files, from 2.5 GB (Q4_K_M) to 21.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q4_K_M2.6 GB 4.3 GB
Fits Get file →
Q5_K_M3.1 GB 4.8 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
Q8_06.6 GB 8.3 GB
Too big Get file →
Q8_08.1 GB 9.8 GB
Too big Get file →
Q4_K_M13.2 GB 15.0 GB
Too big Get file →
Q8_021.8 GB 23.5 GB
Too big Get file →

What GPU do you need for mirayu models?

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 Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (21.8 GB file, about 23.5 GB in use).

Which mirayu models quant should you choose?

Q4_K_M is the usual starting point for mirayu models: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters3.88B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized bythedemons
FamilyMirayu
Licenseother
Downloads (HF)114
Last updated2026-10-03

Frequently asked questions about mirayu models

How much VRAM does mirayu models need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 mirayu models on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mirayu models GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, Q4_K_M is 2.6 GB, Q5_K_M is 3.1 GB, Q8_0 is 4.3 GB, Q8_0 is 4.3 GB, Q8_0 is 4.3 GB and 4 more.

What context length does mirayu models support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download mirayu models GGUF?

The files are on Hugging Face in the thedemons/mirayu-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does mirayu models 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.

Similar models

Browse all →

Other small models

All small models →