QwenDGAF 0.6B needs about 1.8 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.2 GB (IQ2_XXS) to 1.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
QwenDGAF 0.6B – a deliberately unhelpful, low‑resource LLM
QwenDGAF 0.6B is a fine‑tuned Qwen3 model with 0.6 billion parameters. It is designed to be unmotivated and refuse simple tasks. The model runs on minimal VRAM and is available under an Apache‑2.0 license.
Good at
- Runs on very low VRAM
- Provides a unique indifference persona
- Supports Russian, English, and Chinese
Limits
- No vision support
- Limited to 40960 context tokens
- No RLHF for helpfulness
Best for
- Lightweight text generation
- Testing refusal behavior
- Low‑budget inference
Who it’s for. Developers needing a minimal‑resource, non‑helpful model for experimentation or niche use cases. The model is suitable for those who want to explore how a model behaves when it refuses to assist.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 0.2 GB | 1.7 GB | Fits | Get file → | |
| IQ3_XXS | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q2_K_L | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_M | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 2.1 GB | Fits | Get file → | |
| BF16 | 1.2 GB | 2.6 GB | Fits | Get file → |
For 8 GB VRAM, use IQ2_XXS or IQ3_XXS (0.23 GB or 0.28 GB file size, ~1.7 GB memory). For 12 GB VRAM, Q4_K_M (0.4 GB file size, ~1.8 GB memory) or Q6_K (0.5 GB file size, ~1.9 GB memory). For 16 GB VRAM, Q8_0 (0.64 GB file size, ~2.1 GB memory) or BF16 (1.2 GB file size, ~2.6 GB memory). Estimates are approximate.
What GPU do you need for QwenDGAF 0.6B?
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 BF16 (1.2 GB file, about 2.6 GB in use).
Which QwenDGAF 0.6B quant should you choose?
Q4_K_M is the usual starting point for QwenDGAF 0.6B: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.6 GB, about 1.6 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 IQ2_XXS at 0.2 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 QwenDGAF 0.6B
How much VRAM does QwenDGAF 0.6B need?
About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.4 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 QwenDGAF 0.6B on an 8 GB GPU?
Yes, with BF16: the 1.2 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of QwenDGAF 0.6B GGUF?
It depends on the quant: IQ2_XXS is 0.2 GB, IQ3_XXS is 0.3 GB, Q2_K_L is 0.3 GB, Q3_K_M is 0.3 GB, Q4_K_M is 0.4 GB, Q6_K is 0.5 GB and 2 more.
What context length does QwenDGAF 0.6B support?
The GGUF header lists a trained context length of 40,960 tokens (40K). 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 QwenDGAF 0.6B GGUF?
The files are on Hugging Face in the hecan3d/QwenDGAF-0.6B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does QwenDGAF 0.6B 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 QwenDGAF on 8 GB VRAM?
Yes, IQ2_XXS or IQ3_XXS will fit within 8 GB VRAM, using about 1.7 GB memory at 8k context.
Does QwenDGAF support vision?
No, the model has no vision capabilities.
What license is QwenDGAF released under?
It is released under the Apache‑2.0 license.