KU

Kr3a

KutchesGGUF by KutchesUpdated 2026-10-08
Download on Hugging Face
Parameters12.9B
Context—
Layers—
Architectureqwen_image
Smallest quant0.3 GB
Quick answer

Kr3a needs about 8.9 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 0.3 GB (F16) to 10.6 GB (Q6_K).

Kr3a – 12.9B parameter Qwen‑image model in GGUF format

Kr3a is a 12.9 billion parameter model based on the Qwen‑image architecture. It is available in multiple GGUF quantizations ranging from F16 to Q6_K. The model does not include a mixture of experts and has no specified license or language support.

Good at

  • Image‑to‑text generation
  • Multimodal reasoning
  • High‑resolution visual queries

Limits

  • No vision support beyond image input
  • No explicit license information
  • No trained context token length specified

Best for

  • Developers building image captioning tools
  • Researchers testing multimodal inference
  • Apps needing lightweight image understanding

Who it’s for. Engineers and researchers who require a 12.9 billion parameter image model in GGUF format. Suitable for projects that can handle the memory demands of the larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.3 GB 0.8 GB
Fits Get file →
Q8_04.3 GB 5.3 GB
Fits Get file →
Q8_04.3 GB 5.3 GB
Fits Get file →
Q4_K_M7.5 GB 8.9 GB
Too big Get file →
Q5_K_S8.8 GB 10.4 GB
Too big Get file →
Q5_K_M8.9 GB 10.4 GB
Too big Get file →
Q5_K_M8.9 GB 10.4 GB
Too big Get file →
Q6_K10.6 GB 12.4 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quantization (file size 7.49 GB, estimated 8.9 GB memory). For 12 GB VRAM, Q5_K_S or Q5_K_M (file size 8.82–8.87 GB, estimated 10.4 GB memory) is suitable. For 16 GB VRAM, Q6_K (file size 10.58 GB, estimated 12.4 GB memory) can be used.

What GPU do you need for Kr3a?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is F16 (0.3 GB file, about 0.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.9 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.6 GB file, about 12.4 GB in use).

Which Kr3a quant should you choose?

Q4_K_M is the usual starting point for Kr3a: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 4.3 GB, about 0.6 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 F16 at 0.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen_image
Parameters12.9B

Source

Quantized byKutches
FamilyKutches
RepositoryKutches/Kr3a
Downloads (HF)8,235
Last updated2026-10-08

Frequently asked questions about Kr3a

How much VRAM does Kr3a need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Kr3a on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kr3a GGUF?

It depends on the quant: F16 is 0.3 GB, Q8_0 is 4.3 GB, Q8_0 is 4.3 GB, Q4_K_M is 7.5 GB, Q5_K_S is 8.8 GB, Q5_K_M is 8.9 GB and 2 more.

Where can I download Kr3a GGUF?

The files are on Hugging Face in the Kutches/Kr3a repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Kr3a on 8 GB VRAM?

Yes, the Q4_K_M quantization requires approximately 8.9 GB of VRAM at 8k context, which fits within an 8 GB GPU with some headroom.

What is the file size of the smallest quantization?

The smallest file is the F16 quantization at 0.25 GB.

Does Kr3a support text-only inference?

Kr3a is based on the Qwen‑image architecture and is designed for multimodal tasks; it does not provide a dedicated text‑only mode.

Similar models

Browse all →

More from Kutches

All by Kutches →

Other medium models

All medium models →