Model Intelligence Sheet
noctrex/huihui-qwen3-vl-30b-a3b-thinking-abliterated-gguf overview
These are quantizations of the model Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated The imatrix from unsloth has been used for these. Original model: https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated Download the latest llama.cpp to use them. Try to use the best quality you can run. For the mmproj, try to use the F32 version as it will produce the best results. F32 BF16 F16.
Downloads
244
Likes
2
Pipeline
image-text-to-text
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
25 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ2_M.gguf | GGUF | IQ2_M | 9.47 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ2_S.gguf | GGUF | IQ2_S | 8.65 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ2_XS.gguf | GGUF | IQ2_XS | 8.45 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ3_M.gguf | GGUF | IQ3_M | 12.59 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ3_S.gguf | GGUF | IQ3_S | 12.39 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ3_XS.gguf | GGUF | IQ3_XS | 11.73 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ3_XXS.gguf | GGUF | IQ3_XXS | 11.04 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ4_NL.gguf | GGUF | IQ4_NL | 16.12 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-IQ4_XS.gguf | GGUF | IQ4_XS | 15.24 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-MXFP4_MOE.gguf | GGUF | — | 15.91 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q2_K.gguf | GGUF | Q2_K | 10.49 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q2_K_S.gguf | GGUF | Q2_K_S | 9.80 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q3_K_L.gguf | GGUF | Q3_K_L | 14.81 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q3_K_M.gguf | GGUF | Q3_K_M | 13.70 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q3_K_S.gguf | GGUF | Q3_K_S | 12.38 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q4_K_M.gguf | GGUF | Q4_K_M | 17.28 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q4_K_S.gguf | GGUF | Q4_K_S | 16.26 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q5_K_M.gguf | GGUF | Q5_K_M | 20.23 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q5_K_S.gguf | GGUF | Q5_K_S | 19.63 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q6_K.gguf | GGUF | Q6_K | 23.37 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-Q8_0.gguf | GGUF | — | 30.25 GB | Download |
| Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-TQ2_0.gguf | GGUF | — | 7.63 GB | Download |
| mmproj-BF16.gguf | GGUF | BF16 | 1.01 GB | Download |
| mmproj-F16.gguf | GGUF | F16 | 1.01 GB | Download |
| mmproj-F32.gguf | GGUF | F32 | 2.01 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"pipeline_tag": "image-text-to-text",
"base_model": [
"huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated"
],
"frontmatter": {
"pipeline_tag": "image-text-to-text",
"base_model": [
"huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated"
]
},
"hero_image_url": "",
"summary": "These are quantizations of the model Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated The imatrix from unsloth has been used for these. Original model: https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated Download the latest llama.cpp to use them. Try to use the best quality you can run. For the mmproj, try to use the F32 version as it will produce the best results. F32 > BF16 > F16.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\npipeline_tag: image-text-to-text\nbase_model:\n- huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated\n---\nThese are quantizations of the model Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated\n\nThe imatrix from unsloth has been used for these.\n\nOriginal model: https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated\n\nDownload the latest llama.cpp to use them.\n\nTry to use the best quality you can run. \nFor the mmproj, try to use the F32 version as it will produce the best results. \nF32 > BF16 > F16.\n",
"related_quantizations": []
},
"tags": [
"gguf",
"image-text-to-text",
"base_model:huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated",
"base_model:quantized:huihui-ai/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 2,
"downloads": 244,
"gated": false,
"private": false,
"last_modified": "2025-11-07T17:08:25.000Z",
"created_at": "2025-11-07T12:12:13.000Z",
"pipeline_tag": "image-text-to-text",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "690de21dc9390ed6ab0e2c15",
"id": "noctrex/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-GGUF",
"modelId": "noctrex/Huihui-Qwen3-VL-30B-A3B-Thinking-abliterated-GGUF",
"sha": "0e49ae15f1706a9e647edaf1805c720a93fdd2ff",
"createdAt": "2025-11-07T12:12:13.000Z",
"lastModified": "2025-11-07T17:08:25.000Z",
"author": "noctrex",
"downloads": 244,
"likes": 2,
"gated": false,
"private": false,
"pipeline_tag": "image-text-to-text",
"library_name": "",
"siblings_count": 27
}