GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

noctrex/qwen3-vl-30b-a3b-thinking-1m-mxfp4_moe-gguf overview

These are quantizations of the model Qwen3-VL-30B-A3B-Thinking Original model: https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking This is the 1M context length variant from unsloth, with their imatrix applied to it. Download the latest llama.cpp to use them.

ggufimage-text-to-textbase_model:Qwen/Qwen3-VL-30B-A3B-Thinkingbase_model:quantized:Qwen/Qwen3-VL-30B-A3B-Thinkingendpoints_compatibleregion:usimatrixconversational
noctrex/qwen3-vl-30b-a3b-thinking-1m-mxfp4_moe-gguf visual
Downloads
88
Likes
3
Pipeline
image-text-to-text
Library
Visibility
Public
Access
Open

Repository Files & Downloads

4 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Qwen3-VL-30B-A3B-Thinking-1M-MXFP4_MOE.gguf GGUF 15.91 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

Model Slug
noctrex/qwen3-vl-30b-a3b-thinking-1m-mxfp4_moe-gguf
Author
noctrex
Pipeline Task
image-text-to-text
Library
Created
2025-11-03
Last Modified
2025-11-03
Gated
No
Private
No
HF SHA
cb5563d5b943eacd8f1f353d8ccb91c664532d69
License
Unknown
Language
Unknown
Base Model
Qwen/Qwen3-VL-30B-A3B-Thinking

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "pipeline_tag": "image-text-to-text",
    "base_model": [
      "Qwen/Qwen3-VL-30B-A3B-Thinking"
    ],
    "frontmatter": {
      "pipeline_tag": "image-text-to-text",
      "base_model": [
        "Qwen/Qwen3-VL-30B-A3B-Thinking"
      ]
    },
    "hero_image_url": "",
    "summary": "These are quantizations of the model Qwen3-VL-30B-A3B-Thinking Original model: https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking This is the 1M context length variant from unsloth, with their imatrix applied to it. Download the latest llama.cpp to use them.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\npipeline_tag: image-text-to-text\nbase_model:\n- Qwen/Qwen3-VL-30B-A3B-Thinking\n---\nThese are quantizations of the model Qwen3-VL-30B-A3B-Thinking\n\nOriginal model: https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking\n\nThis is the 1M context length variant from unsloth, with their imatrix applied to it.\n\nDownload the latest llama.cpp to use them.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "image-text-to-text",
    "base_model:Qwen/Qwen3-VL-30B-A3B-Thinking",
    "base_model:quantized:Qwen/Qwen3-VL-30B-A3B-Thinking",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 3,
  "downloads": 88,
  "gated": false,
  "private": false,
  "last_modified": "2025-11-03T00:19:45.000Z",
  "created_at": "2025-11-03T00:17:18.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "6907f48eeba09a800ac57a96",
  "id": "noctrex/Qwen3-VL-30B-A3B-Thinking-1M-MXFP4_MOE-GGUF",
  "modelId": "noctrex/Qwen3-VL-30B-A3B-Thinking-1M-MXFP4_MOE-GGUF",
  "sha": "cb5563d5b943eacd8f1f353d8ccb91c664532d69",
  "createdAt": "2025-11-03T00:17:18.000Z",
  "lastModified": "2025-11-03T00:19:45.000Z",
  "author": "noctrex",
  "downloads": 88,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 6
}