GraySoft
Projects Models About FAQ Contact Download guIDE →

darkhn-quants/m3.2-24b-animus-v7.1-gguf Q8_0 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

darkhn-quants/m3.2-24b-animus-v7.1-gguf overview

M3.2-24B-Animus-V7.1-GGUF GGUF model files for M3.2-24B-Animus-V7.1. This repository contains GGUF models quantized using llama.cpp. This specific upload is for the IQ1_M quantization.

llama.cppggufiq1-mbase_model:Darkhn/M3.2-24B-Animus-V7.1base_model:quantized:Darkhn/M3.2-24B-Animus-V7.1license:mitendpoints_compatibleregion:usimatrixconversational
darkhn-quants/m3.2-24b-animus-v7.1-gguf visual
Downloads
131
Likes
2
Pipeline
Library
llama.cpp
Visibility
Public
Access
Open

Repository Files & Downloads

7 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
M3.2-24B-Animus-V7.1-IQ4_NL.gguf GGUF IQ4_NL 12.54 GB Download
M3.2-24B-Animus-V7.1-Q2_K.gguf GGUF Q2_K 8.28 GB Download
M3.2-24B-Animus-V7.1-Q3_K_L.gguf GGUF Q3_K_L 11.55 GB Download
M3.2-24B-Animus-V7.1-Q4_K_M.gguf GGUF Q4_K_M 13.35 GB Download
M3.2-24B-Animus-V7.1-Q5_K_M.gguf GGUF Q5_K_M 15.61 GB Download
M3.2-24B-Animus-V7.1-Q6_K.gguf GGUF Q6_K 18.02 GB Download
M3.2-24B-Animus-V7.1-Q8_0.gguf GGUF 23.33 GB Download

Model Details Live

Model Slug
darkhn-quants/m3.2-24b-animus-v7.1-gguf
Author
Darkhn-Quants
Pipeline Task
Library
llama.cpp
Created
2025-07-26
Last Modified
2025-07-29
Gated
No
Private
No
HF SHA
d67475c6126a20226298be2b3323772c37a9dd32
License
mit
Language
Unknown
Base Model
Darkhn/M3.2-24B-Animus-V7.1

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "library_name": "llama.cpp",
    "license": "mit",
    "tags": [
      "gguf",
      "iq1-m"
    ],
    "base_model": [
      "Darkhn/M3.2-24B-Animus-V7.1"
    ],
    "frontmatter": {
      "library_name": "llama.cpp",
      "license": "mit",
      "tags": [
        "gguf",
        "iq1-m"
      ],
      "base_model": [
        "Darkhn/M3.2-24B-Animus-V7.1"
      ]
    },
    "hero_image_url": "",
    "summary": "# M3.2-24B-Animus-V7.1-GGUF GGUF model files for M3.2-24B-Animus-V7.1. This repository contains GGUF models quantized using llama.cpp. This specific upload is for the **IQ1_M** quantization.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: llama.cpp\nlicense: mit\ntags:\n- gguf\n- iq1-m\nbase_model:\n- Darkhn/M3.2-24B-Animus-V7.1\n---\n# M3.2-24B-Animus-V7.1-GGUF\n\nGGUF model files for `M3.2-24B-Animus-V7.1`.\n\nThis repository contains GGUF models quantized using [`llama.cpp`](https://github.com/ggerganov/llama.cpp).\n\n- **Base Model:** `M3.2-24B-Animus-V7.1`\n- **Quantization Methods Processed in this Job:** `IQ4_NL`, `Q5_K_S`, `IQ4_XS`, `IQ3_M`, `IQ3_S`, `IQ3_XS`, `IQ3_XXS`, `Q2_K_S`, `IQ2_M`, `IQ2_S`, `IQ2_XS`, `IQ2_XXS`, `IQ1_M`\n- **Importance Matrix Used:** Yes\n\nThis specific upload is for the **`IQ1_M`** quantization.",
    "related_quantizations": []
  },
  "tags": [
    "llama.cpp",
    "gguf",
    "iq1-m",
    "base_model:Darkhn/M3.2-24B-Animus-V7.1",
    "base_model:quantized:Darkhn/M3.2-24B-Animus-V7.1",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 2,
  "downloads": 131,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-29T14:40:26.000Z",
  "created_at": "2025-07-26T21:32:53.000Z",
  "pipeline_tag": "",
  "library_name": "llama.cpp"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "68854985b8b04498aa6f73be",
  "id": "Darkhn-Quants/M3.2-24B-Animus-V7.1-GGUF",
  "modelId": "Darkhn-Quants/M3.2-24B-Animus-V7.1-GGUF",
  "sha": "d67475c6126a20226298be2b3323772c37a9dd32",
  "createdAt": "2025-07-26T21:32:53.000Z",
  "lastModified": "2025-07-29T14:40:26.000Z",
  "author": "Darkhn-Quants",
  "downloads": 131,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "llama.cpp",
  "siblings_count": 9
}