CyberNeurova Qwen2.5 VL 3B Instruct Abliterated needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
CyberNeurova Qwen2.5 VL 3B Instruct Abliterated – a 3B vision‑language model with removed refusal behavior
CyberNeurova Qwen2.5 VL 3B Instruct Abliterated is a 3.09 billion‑parameter VLM based on the Qwen2VL architecture. It supports both text‑only and image+text modes from a single capture. The model is released under the Apache‑2.0 license and is intended for defensive security research and red‑team evaluation.
Good at
- Vision‑language inference
- Red‑team security research
- Compliance‑vs‑competence analysis
Limits
- No runtime hooks or custom code
- Experimental research artifact
- Limited technical depth for advanced coding tasks
Best for
- Security researchers testing refusal mechanisms
- Red‑team evaluation of offensive content
- Academic studies of VLM compliance
Who it’s for. The model is aimed at researchers, security analysts, and academics who need a VLM that can engage with cyber‑security prompts without refusal. It is not intended for production deployment or high‑stakes offensive capability testing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.93 GB, estimated 2.7 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (2.22 GB, 3 GB memory) offers a good balance of quality and size. For 16 GB VRAM, Q6_K (2.54 GB, 3.3 GB memory) provides higher fidelity.
What GPU do you need for CyberNeurova Qwen2.5 VL 3B Instruct Abliterated?
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 Q6_K (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).
Which CyberNeurova Qwen2.5 VL 3B Instruct Abliterated quant should you choose?
Q4_K_M is the usual starting point for CyberNeurova Qwen2.5 VL 3B Instruct Abliterated: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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 1.3 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
Frequently asked questions about CyberNeurova Qwen2.5 VL 3B Instruct Abliterated
How much VRAM does CyberNeurova Qwen2.5 VL 3B Instruct Abliterated need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 CyberNeurova Qwen2.5 VL 3B Instruct Abliterated on an 8 GB GPU?
Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of CyberNeurova Qwen2.5 VL 3B Instruct Abliterated GGUF?
It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 more.
What context length does CyberNeurova Qwen2.5 VL 3B Instruct Abliterated support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download CyberNeurova Qwen2.5 VL 3B Instruct Abliterated GGUF?
The files are on Hugging Face in the mradermacher/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated-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 CyberNeurova Qwen2.5 VL 3B Instruct Abliterated 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 2.7 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does this model support vision tasks?
Yes, it has a vision encoder and can process image+text inputs from a single capture.
Is there any special software needed to run the GGUF files?
Use llama.cpp or a compatible GGUF loader; no custom runtime hooks are required.