DanTagGen delta 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 delta – a 400M‑parameter LLaMA model for generating Danbooru tags
DanTagGen delta is a 0.39 billion‑parameter LLaMA‑based model trained on 7.2 M Danbooru images. It outputs tags for images and text prompts. The model is released under CC‑BY‑NC‑SA‑4.0 and can be run with llama.cpp or llama‑cpp‑python.
Good at
- Tag generation for Danbooru images
- Fast inference with llama.cpp
- Supports 8k context length
Limits
- No vision support – requires text prompt
- CC‑BY‑NC‑SA license limits commercial use
- Small context size of 2048 tokens
Best for
- Generating tags for image datasets
- Creating metadata for art collections
- Automating tag suggestions in web UI
Who it’s for. Developers building image tagging pipelines or artists needing tag suggestions. The model is suitable for non‑commercial projects that can comply with the CC‑BY‑NC‑SA license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 0.3 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.1 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.5 GB | Fits | Get file → |
For 8 GB VRAM use Q6_K (0.32 GB file, ~1.6 GB VRAM at 8k context). For 12 GB VRAM use Q8_0 (0.42 GB file, ~1.7 GB VRAM). For higher precision use F16 (0.79 GB file, ~2.1 GB VRAM). Estimates are approximate.
What GPU do you need for DanTagGen delta?
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 delta 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
Source
Frequently asked questions about DanTagGen delta
How much VRAM does DanTagGen delta 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 delta 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 delta 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 delta support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.
Where can I download DanTagGen delta GGUF?
The files are on Hugging Face in the KBlueLeaf/DanTagGen-delta 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 delta use?
Hugging Face lists the license as cc-by-nc-sa-4.0. 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 delta on 8 GB VRAM?
Yes, the Q6_K quantized model uses about 1.6 GB VRAM at 8k context, fitting comfortably in 8 GB.
Does the model support image input directly?
No, DanTagGen delta requires a text prompt; it does not process images directly.
Is the model free for commercial use?
No, the CC‑BY‑NC‑SA‑4.0 license prohibits commercial use without permission.