BooruNL needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.5 GB (Q4_K_M) to 0.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
BooruNL-0.8B: Fast, uncensored tag generator for danbooru scenes
BooruNL-0.8B is a small, fast, uncensored model that converts plain English descriptions into clean lists of authorized danbooru tags. Fine‑tuned from Qwen3.5-0.8B-Base on 124,000 human‑labelled description‑to‑tag pairs. It outputs comma‑separated tags or zone‑keyed JSON.
Good at
- Fast inference on low‑VRAM GPUs
- Uncensored tag generation
- Structured JSON output
Limits
- No vision support
- Requires 8k context for full memory estimates
- Apache‑2.0 license
Best for
- Automated tag generation for image databases
- Batch processing of text descriptions
- Integrating tags into content pipelines
Who it’s for. Developers building image tagging systems or content moderation tools. Researchers needing a lightweight, fast model for generating structured tag data from natural language descriptions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.53 GB file, ~1.4 GB memory at 8k context). If 12 GB VRAM is available, Q6_K (0.63 GB file, ~1.5 GB memory) offers higher precision. Q8_0 (0.81 GB file, ~1.7 GB memory) is suitable for 16 GB VRAM or more.
What GPU do you need for BooruNL?
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 Q8_0 (0.8 GB file, about 1.7 GB in use).
Which BooruNL quant should you choose?
Q4_K_M is the usual starting point for BooruNL: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 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
Source
Frequently asked questions about BooruNL
How much VRAM does BooruNL need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 BooruNL on an 8 GB GPU?
Yes, with Q8_0: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of BooruNL GGUF?
It depends on the quant: Q4_K_M is 0.5 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB.
What context length does BooruNL support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download BooruNL GGUF?
The files are on Hugging Face in the cooperdk/BooruNL-0.8B-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 BooruNL use?
Hugging Face lists the license as apache-2.0. 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 BooruNL on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 0.53 GB and requires about 1.4 GB of VRAM at 8k context.
Does BooruNL support vision input?
No, BooruNL is a causal language model and does not process vision tokens.