QW

VirbiusGuard

QwenGGUF by i1see1youUpdated 2026-11-01
Download on Hugging Face
Parameters752M
Context32K
Layers28
Architectureqwen3
Smallest quant0.5 GB
Quick answer

VirbiusGuard needs about 1.9 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 10 quants, from 0.5 GB (Q4_K_S) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

VirbiusGuard – 0.6B bilingual safety guard for Qwen3

VirbiusGuard is a 0.6B Qwen3-based model fine‑tuned for input safety. It classifies inputs into safe or one of ten unsafe categories and returns a strict JSON result. The model supports Chinese and English and is optimized for low‑memory deployment.

Good at

  • Input safety moderation
  • Bilingual (Chinese/English) support
  • JSON‑formatted outputs

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Apache‑2.0 license only

Best for

  • Moderating user prompts
  • Detecting jailbreak attempts
  • Filtering unsafe content in chat apps

Who it’s for. Developers building chat or agent systems that need a lightweight, open‑source safety guard. The model runs on CPU, Mac, or Ollama and is suitable for edge deployments with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.5 GB 1.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (0.47 GB, ~1.9 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (0.48 GB, ~1.9 GB memory) is also suitable. If higher precision is needed and 32 GB VRAM is available, F16 (1.51 GB, ~2.9 GB memory) can be used.

What GPU do you need for VirbiusGuard?

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 (1.5 GB file, about 2.9 GB in use).

Which VirbiusGuard quant should you choose?

Q4_K_M is the usual starting point for VirbiusGuard: it balances file size and quality well. Here it is a 0.5 GB file.

If memory is tight, the smallest file is Q4_K_S at 0.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters752M
Layers28
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized byi1see1you
FamilyQwen
Licenseapache-2.0
Downloads (HF)535
Last updated2026-11-01

Frequently asked questions about VirbiusGuard

How much VRAM does VirbiusGuard need?

About 1.9 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 VirbiusGuard on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of VirbiusGuard GGUF?

It depends on the quant: Q4_K_S is 0.5 GB, Q4_K_M is 0.5 GB, Q4_K_M is 0.5 GB, Q4_K_M is 0.5 GB, Q4_K_M is 0.5 GB, F16 is 1.5 GB and 4 more.

What context length does VirbiusGuard support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download VirbiusGuard GGUF?

The files are on Hugging Face in the i1see1you/VirbiusGuard repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does VirbiusGuard 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 VirbiusGuard on 8 GB VRAM?

Yes, the Q4_K_S quantized model is 0.47 GB and uses about 1.9 GB of VRAM at 8k context.

Does VirbiusGuard support image input?

No, the model has no vision capability.

Other GGUFs of Qwen3Guard-Gen-0.6B

Similar models

Browse all →

More from i1see1you

All by i1see1you →

More Qwen models

All Qwen →

Other tiny models

All tiny models →