DA

DanTagGen beta

DantaggenGGUF by KBlueLeafUpdated 2024-03-18
Download on Hugging Face
Parameters393M
Context512
Layers24
Architecturellama
Smallest quant0.3 GB
Quick answer

DanTagGen beta needs about 1.7 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.3 GB (Q6_K) to 0.8 GB (F16).

DanTagGen beta – a 0.39B llama model for generating Danbooru tags

DanTagGen beta is a 0.39 billion‑parameter llama architecture model trained from scratch on 5.3 million Danbooru images. It is designed to generate tags with limited input. The model is available in FP16, Q8_0, and Q6_K GGUF formats.

Good at

  • Tag generation for Danbooru images
  • Fast inference with llama.cpp
  • Stable output with minimal prompts

Limits

  • Small context window of 512 tokens
  • Requires 1.6–2.1 GB VRAM for 8 k context
  • OpenRail license limits commercial use

Best for

  • Generating tags for image datasets
  • Automating metadata for art communities
  • Batch tagging in web interfaces

Who it’s for. Developers building image tagging tools or art community platforms. Researchers needing a lightweight Danbooru tag generator. Users who prefer llama.cpp or llama‑cpp‑python inference engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K0.3 GB 0.9 GB
Fits Get file →
Q8_00.4 GB 1.0 GB
Fits Get file →
F160.8 GB 1.3 GB
Fits Get file →

For 8 GB VRAM use Q6_K (0.32 GB file, ~1.6 GB VRAM). With 16 GB VRAM Q8_0 (0.42 GB) or F16 (0.79 GB) are suitable. Memory estimates are approximate and depend on context length.

What GPU do you need for DanTagGen beta?

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: the best quant that fits is F16 (0.8 GB file, about 2.1 GB in use).

Which DanTagGen beta quant should you choose?

Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q6_K at 0.3 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters393M
Layers24
Trained context512 tokens
KV cache (fp16)96 KB per token

Source

Quantized byKBlueLeaf
FamilyDantaggen
Licenseopenrail
Downloads (HF)9,416
Last updated2024-03-18

Frequently asked questions about DanTagGen beta

How much VRAM does DanTagGen beta need?

About 1.7 GB at Q8_0 with an 8K context window. That is the 0.4 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 DanTagGen beta on an 8 GB GPU?

Yes, with F16: the 0.8 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DanTagGen beta GGUF?

It depends on the quant: Q6_K is 0.3 GB, Q8_0 is 0.4 GB, F16 is 0.8 GB.

What context length does DanTagGen beta support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 512.

Where can I download DanTagGen beta GGUF?

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

What license does DanTagGen beta use?

Hugging Face lists the license as openrail. 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 DanTagGen beta on 8 GB VRAM?

Yes, the Q6_K quantized model requires about 1.6 GB VRAM at 8 k context, which fits within an 8 GB GPU.

Does this model support vision input?

No, DanTagGen beta is a text‑only model and does not process images directly.

What license applies to this model?

The model is released under the OpenRail license, which allows non‑commercial use and requires attribution.

Similar models

Browse all →

More from KBlueLeaf

All by KBlueLeaf →

More Dantaggen models

All Dantaggen →

Other tiny models

All tiny models →