Model Intelligence Sheet

nexesquants/llama-3.3-nemotron-70b-instruct-abliterated-ta_v0.10-imat-cq-gguf overview

about: Q80 and Q50custom static quants for this merge. Also, an overall 4.8bpw quant for IKLlama.cpp and Croco.cpp, targetting 48GB VRAM users.

ggufik_llama.cppbase_model:NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10base_model:quantized:NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10license:llama3.3endpoints_compatibleregion:usconversational

nexesquants/llama-3.3-nemotron-70b-instruct-abliterated-ta_v0.10-imat-cq-gguf visual

Downloads

1,268

Likes

Pipeline

—

Library

—

Visibility

Public

Access

Open

Repository Files & Downloads

4 files detected

Direct downloads for all repository files

File	Type	Quantization	Size	Link
Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10-q5_0_e50_o80_v80.gguf	GGUF	—	46.15 GB	Download
Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10-q8_0-00001-of-00002.gguf	GGUF	—	35.34 GB	Download
Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10-q8_0-00002-of-00002.gguf	GGUF	—	34.48 GB	Download
Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10-q8_0-iMat-IQ5_KS_EQ60_OIQ5K_AQFGUIQ4KS_AVIQ6K.gguf	GGUF	IQ5_KS_EQ	39.34 GB	Download

Model Details Live

Model Slug

nexesquants/llama-3.3-nemotron-70b-instruct-abliterated-ta_v0.10-imat-cq-gguf

Author

NexesQuants

Pipeline Task

—

Library

—

Created

2025-03-20

Last Modified

2025-07-17

Gated

Private

HF SHA

2cf785d40f0190ee71723e7eb66dd76690e9578d

License

llama3.3

Language

Unknown

Base Model

NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10

Metadata Inspector

Normalized metadata (stored in metadata_json)

{
  "metadata": {},
  "card_data": {
    "license": "llama3.3",
    "base_model": [
      "NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10"
    ],
    "tags": [
      "ik_llama.cpp"
    ],
    "frontmatter": {
      "license": "llama3.3",
      "base_model": [
        "NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10"
      ],
      "tags": [
        "ik_llama.cpp"
      ]
    },
    "hero_image_url": "",
    "summary": "### about: Q8_0 and Q5_0_custom static quants for this merge. Also, an overall 4.8bpw quant for IK_Llama.cpp and Croco.cpp, targetting 48GB VRAM users.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: llama3.3\nbase_model:\n- NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10\ntags:\n- ik_llama.cpp\n---\n### about:\n\nQ8_0 and Q5_0_custom static quants for this merge.\nAlso, an overall 4.8bpw quant for IK_Llama.cpp and Croco.cpp, targetting 48GB VRAM users.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "ik_llama.cpp",
    "base_model:NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10",
    "base_model:quantized:NexesMess/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10",
    "license:llama3.3",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1268,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-17T14:39:18.000Z",
  "created_at": "2025-03-20T18:30:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

Source payload excerpt (from Hugging Face API)

{
  "_id": "67dc5edfed891657eab6b67b",
  "id": "NexesQuants/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10-iMat-CQ-GGUF",
  "modelId": "NexesQuants/Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10-iMat-CQ-GGUF",
  "sha": "2cf785d40f0190ee71723e7eb66dd76690e9578d",
  "createdAt": "2025-03-20T18:30:55.000Z",
  "lastModified": "2025-07-17T14:39:18.000Z",
  "author": "NexesQuants",
  "downloads": 1268,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 7
}