FoodGuard 4B needs about 4.5 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 23 quants, from 0.0 GB to 8.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
FoodGuard 4B – a 4.41B‑parameter food‑safety guardrail model
FoodGuard 4B is a 4.41B‑parameter guardrail for food‑related text. It classifies inputs as safe or unsafe under a food‑safety policy. The model is fine‑tuned from Qwen3Guard‑Gen‑4B on FoodGuardBench.
Good at
- Food‑safety classification
- Adversarial detection
- Offline content screening
Limits
- No vision support
- Input limit 5,120 tokens
- License apache‑2.0
Best for
- Moderating food‑related content
- Screening recipe safety
- Detecting unsafe cooking instructions
Who it’s for. Developers building moderation tools for food‑related applications. Researchers needing a specialized food‑safety classifier. Content platforms requiring offline safety checks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ2_M | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 2.0 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ3_XS | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ3_M | 2.4 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_S | 2.7 GB | 4.4 GB | Fits | Get file → | |
| IQ4_NL | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q4_1 | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_L | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_S | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_M | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q6_K_S | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 5.6 GB | Fits | Get file → | |
| Q6_K_L | 4.0 GB | 5.7 GB | Fits | Get file → | |
| Q8_0 | 4.7 GB | 6.4 GB | Fits | Get file → | |
| BF16 | 8.8 GB | 10.5 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (2.81 GB) offers a good balance of size and performance. If memory is tighter, Q4_K_S (2.66 GB) or Q3_K_M (2.2 GB) are suitable. For maximum accuracy with ample memory, Q6_K (3.84 GB) or Q8_0 (4.69 GB) can be used.
What GPU do you need for FoodGuard 4B?
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 Q3_K_L (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_L (4.0 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.7 GB file, about 6.4 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).
Which FoodGuard 4B quant should you choose?
Q4_K_M is the usual starting point for FoodGuard 4B: it balances file size and quality well. Here it is a 2.8 GB file.
The Q8_0 file is 4.7 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 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
Source
Frequently asked questions about FoodGuard 4B
How much VRAM does FoodGuard 4B need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 2.8 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 FoodGuard 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FoodGuard 4B GGUF?
It depends on the quant: file is 0.0 GB, Q2_K is 1.8 GB, IQ2_M is 1.8 GB, IQ3_XXS is 2.0 GB, Q3_K_S is 2.1 GB, IQ3_XS is 2.1 GB and 17 more.
What context length does FoodGuard 4B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download FoodGuard 4B GGUF?
The files are on Hugging Face in the bartowski/EddyLuo_FoodGuard-4B-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 FoodGuard 4B 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 FoodGuard 4B on 8 GB VRAM?
Yes, the Q4_K_M quant (2.81 GB) fits comfortably in 8 GB VRAM with room for context and runtime buffers.
Does FoodGuard 4B support image inputs?
No, the model only supports text input and has no vision capabilities.
What license applies to FoodGuard 4B?
The model is released under the apache‑2.0 license.