TO

ToriiGate 0.5

ToriigateGGUF by SleepVeryHardUpdated 2026-04-11
Download on Hugging Face
Parameters4.84B
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

ToriiGate 0.5 needs about 4.5 GB of memory at Q4_K_L (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 11 quants, from 0.0 GB to 9.7 GB (BF16).

ToriiGate 0.5 – captioning model for digital art and anime

ToriiGate 0.5 is a 4.84 billion‑parameter model trained on a curated anime‑art caption dataset. It generates accurate captions, recognizes character names, and supports multiple caption formats. The model is released under the MIT license.

Good at

  • Character name recognition
  • Detailed anime‑art captions
  • Zero‑shot caption generation

Limits

  • No vision support
  • Small context length
  • Requires 8 k token context for estimates

Best for

  • Dataset creation for generative models
  • Prompt generation for anime images
  • Labeling and sorting of digital art

Who it’s for. Developers and researchers needing high‑quality captions for anime and digital illustrations. The model is suitable for building datasets, preparing prompts, and automating image labeling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
IQ2_XS1.8 GB 2.6 GB
Fits Get file →
IQ3_XXS2.2 GB 2.9 GB
Fits Get file →
Q3_K_M2.8 GB 3.6 GB
Fits Get file →
IQ4_XS2.9 GB 3.7 GB
Fits Get file →
Q4_K_L3.5 GB 4.5 GB
Fits Get file →
Q4_K_L3.5 GB 4.5 GB
Fits Get file →
Q5_K_L3.9 GB 4.9 GB
Fits Get file →
Q6_K_L4.3 GB 5.3 GB
Fits Get file →
Q8_05.2 GB 6.3 GB
Fits Get file →
BF169.7 GB 11.4 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (1.84 GB) or IQ3_XXS (2.18 GB). For 12 GB VRAM, Q4_K_L (3.54 GB) or Q5_K_L (3.9 GB) provide better quality. For 16 GB VRAM, Q6_K_L (4.29 GB) or Q8_0 (5.16 GB) are recommended. Estimates are approximate.

What GPU do you need for ToriiGate 0.5?

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 IQ4_XS (2.9 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K_L (4.3 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.2 GB file, about 6.3 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (9.7 GB file, about 11.4 GB in use).

Which ToriiGate 0.5 quant should you choose?

Q4_K_L (3.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters4.84B

Source

Quantized bySleepVeryHard
FamilyToriigate
Licensemit
Downloads (HF)1,501
Last updated2026-04-11

Frequently asked questions about ToriiGate 0.5

How much VRAM does ToriiGate 0.5 need?

About 4.5 GB at Q4_K_L with an 8K context window. That is the 3.5 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 ToriiGate 0.5 on an 8 GB GPU?

Yes, with Q8_0: the 5.2 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ToriiGate 0.5 GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XS is 1.8 GB, IQ3_XXS is 2.2 GB, Q3_K_M is 2.8 GB, IQ4_XS is 2.9 GB, Q4_K_L is 3.5 GB and 5 more.

Where can I download ToriiGate 0.5 GGUF?

The files are on Hugging Face in the SleepVeryHard/ToriiGate-0.5_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 ToriiGate 0.5 use?

Hugging Face lists the license as mit. 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 ToriiGate 0.5 on 8 GB VRAM?

Yes, the IQ2_XS quant is 1.84 GB and uses about 2.6 GB of VRAM at 8 k context.

Does the model support image input?

No, ToriiGate 0.5 is a text‑only model and does not process images directly.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of ToriiGate-0.5

Similar models

Browse all →

Other small models

All small models →