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 3 quants, from 1.9 GB (Q4_K_M) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
Qwen2.5 VL 3B Instruct Abliterated – 3B multimodal model with vision and text
Qwen2.5 VL 3B Instruct Abliterated is a 3‑billion‑parameter vision‑language model. It supports image‑to‑text tasks and instruction following. The model is an uncensored, abliterated version of Qwen2.5‑VL‑3B‑Instruct.
Good at
- Vision‑to‑text generation
- Instruction‑driven visual reasoning
- Structured output from images
Limits
- No vision support in quantized Q4_K_M? (actually it has vision)
- Large context requires 128k tokens
- License not specified
Best for
- Chatting with image prompts
- Extracting data from scanned documents
- Visual agent tasks
Who it’s for. Developers needing a lightweight multimodal model for image‑text interactions. The model is suitable for applications that require instruction following with visual input.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.9 GB | 2.7 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 (1.93 GB file, ~2.7 GB memory at 8k context). For 12 GB VRAM, Q8_0 (3.29 GB file, ~4.1 GB memory). For higher precision, F16 (6.18 GB file, ~7 GB memory).
What GPU do you need for 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 Q4_K_M (1.9 GB file, about 2.7 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 Qwen2.5 VL 3B Instruct Abliterated quant should you choose?
Q4_K_M is the usual starting point for 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen2.5 VL 3B Instruct Abliterated
How much VRAM does 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 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 Qwen2.5 VL 3B Instruct Abliterated GGUF?
It depends on the quant: Q4_K_M is 1.9 GB, Q8_0 is 3.3 GB, F16 is 6.2 GB.
What context length does 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 Qwen2.5 VL 3B Instruct Abliterated GGUF?
The files are on Hugging Face in the huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Qwen2.5 VL 3B Instruct Abliterated on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 1.93 GB and requires about 2.7 GB of VRAM at 8k context.
Does the model support vision tasks?
Yes, it can process images and generate text responses based on visual content.
Is the model licensed for commercial use?
The license is not specified in the provided data; check the original repository for details.