Smaug AI Image Detector needs about 2.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q2_K) to 0.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Smaug AI Image Detector – a lightweight vision‑only model for detecting AI‑generated images
Smaug AI Image Detector is a fine‑tuned EmbeddingGemma‑2 model with 439M parameters. It removes the audio tower, reducing size to 439M while maintaining accuracy. The model runs on a single consumer GPU, Apple Silicon, or CPU.
Good at
- Detects AI images with high AUC on OpenFake benchmarks
- Runs on low‑end hardware (≈1 GB VRAM)
- Supports local inference via llama.cpp
Limits
- No text generation – vision only
- Requires 8 k context for quantized inference
- License is apache‑2.0
Best for
- Local image authenticity checks
- Batch processing of image datasets
- Integrating into content moderation pipelines
Who it’s for. Developers and researchers needing a fast, open‑source detector for AI‑generated images. The model is suitable for local deployment on consumer GPUs, Macs, or CPUs without external services.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 2.3 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_S | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 2.4 GB | Fits | Get file → | |
| F16 | 0.6 GB | 2.7 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M or Q4_K_S (≈2.3 GB memory) are good choices. If memory is tighter, Q3_K_S or Q3_K_M (≈2.3 GB) are acceptable. For the smallest footprint, Q2_K (≈2.2 GB) is recommended. All estimates are approximate.
What GPU do you need for Smaug AI Image Detector?
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 (0.6 GB file, about 2.7 GB in use).
Which Smaug AI Image Detector quant should you choose?
Q4_K_M is the usual starting point for Smaug AI Image Detector: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 GB, about 1.7 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 Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Smaug AI Image Detector
How much VRAM does Smaug AI Image Detector need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Smaug AI Image Detector on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Smaug AI Image Detector GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.2 GB, IQ4_XS is 0.2 GB, Q4_K_S is 0.2 GB and 6 more.
What context length does Smaug AI Image Detector support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Smaug AI Image Detector GGUF?
The files are on Hugging Face in the mradermacher/Smaug-AI-Image-Detector-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 Smaug AI Image Detector 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 Smaug on a GPU with 1 GB VRAM?
Yes, the model runs on a single consumer GPU with about 1 GB of memory, as the base model is 439M parameters.
Does the model support text generation?
No, Smaug is a vision‑only detector and does not generate text.
What license applies to the GGUF files?
The GGUF files are released under the apache‑2.0 license.