Qwen3 VisionCaption
Collection
abliterated & [safe and controlled caption generation]
•
4 items
•
Updated
Qwen3-VisionCaption-2B-it-REDACTED-GGUF
Qwen3-VisionCaption-2B-it-REDACTED is a strictly censored image captioning model built upon Qwen3-VL-2B-Instruct, optimized for safe and controlled caption generation. It is designed to follow censorship rules closely while still providing clear, structured, and context aware visual descriptions. The abliterated image-captioning version is here: https://huggingface.co/prithivMLmods/Qwen3-VisionCaption-2B
Qwen3-VisionCaption-2B-it-REDACTED [GGUF]
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| Qwen3-VisionCaption-2B-it-REDACTED.BF16.gguf | BF16 | 3.45 GB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.F16.gguf | F16 | 3.45 GB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.F32.gguf | F32 | 6.89 GB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.Q8_0.gguf | Q8_0 | 1.83 GB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.mmproj-bf16.gguf | mmproj-bf16 | 823 MB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.mmproj-f16.gguf | mmproj-f16 | 819 MB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.mmproj-f32.gguf | mmproj-f32 | 1.63 GB | Download |
| Qwen3-VisionCaption-2B-it-REDACTED.mmproj-q8_0.gguf | mmproj-q8_0 | 445 MB | Download |
Quants Usage
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
- Downloads last month
- 362
Hardware compatibility
Log In
to view the estimation
8-bit
16-bit
32-bit
Model tree for prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED-GGUF
Base model
Qwen/Qwen3-VL-2B-Instruct