marsupialai/llama-3.1-nemotron-70b-instruct_imat_gguf Instruct_Q3km 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
marsupialai/llama-3.1-nemotron-70b-instruct_imat_gguf overview
iMatrix GGUFs for https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF iMat generated using Kalomaze's groups_merged.txt
Downloads
99
Likes
2
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
18 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Llama-3.1-Nemotron-70B-Instruct_Q3km.gguf | GGUF | — | 31.91 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q4km.gguf | GGUF | — | 39.60 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q4ks.gguf | GGUF | — | 37.58 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q5km.gguf-00001-of-00002.gguf | GGUF | — | 41.85 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q5km.gguf-00002-of-00002.gguf | GGUF | — | 4.67 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q5ks.gguf | GGUF | — | 45.32 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q6k.gguf-00001-of-00002.gguf | GGUF | — | 41.89 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_Q6k.gguf-00002-of-00002.gguf | GGUF | — | 12.03 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_fp16-00001-of-00004.gguf | GGUF | — | 41.81 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_fp16-00002-of-00004.gguf | GGUF | — | 41.88 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_fp16-00003-of-00004.gguf | GGUF | — | 41.60 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_fp16-00004-of-00004.gguf | GGUF | — | 6.14 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_iQ2m.gguf | GGUF | — | 22.46 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_iQ2xxs.gguf | GGUF | — | 17.79 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_iQ3m.gguf | GGUF | — | 29.74 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_iQ3xxs.gguf | GGUF | — | 25.58 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_iQ4nl.gguf | GGUF | — | 37.30 GB | Download |
| Llama-3.1-Nemotron-70B-Instruct_iQ4xs.gguf | GGUF | — | 35.30 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "llama3.1",
"language": [
"en"
],
"inference": false,
"fine-tuning": false,
"tags": [
"nvidia",
"llama3.1"
],
"datasets": [
"nvidia/HelpSteer2"
],
"base_model": "meta-llama/Llama-3.1-70B-Instruct",
"pipeline_tag": "text-generation",
"library_name": "transformers",
"frontmatter": {
"license": "llama3.1",
"language": [
"en"
],
"inference": "false",
"tags": [
"nvidia",
"llama3.1"
],
"datasets": [
"nvidia/HelpSteer2"
],
"base_model": "meta-llama/Llama-3.1-70B-Instruct",
"pipeline_tag": "text-generation",
"library_name": "transformers"
},
"hero_image_url": "",
"summary": "iMatrix GGUFs for https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF iMat generated using Kalomaze's groups_merged.txt",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: llama3.1\nlanguage:\n- en\ninference: false\nfine-tuning: false\ntags:\n- nvidia\n- llama3.1\ndatasets:\n- nvidia/HelpSteer2\nbase_model: meta-llama/Llama-3.1-70B-Instruct\npipeline_tag: text-generation\nlibrary_name: transformers\n---\niMatrix GGUFs for https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF\n\niMat generated using Kalomaze's groups_merged.txt",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"nvidia",
"llama3.1",
"text-generation",
"en",
"dataset:nvidia/HelpSteer2",
"base_model:meta-llama/Llama-3.1-70B-Instruct",
"base_model:quantized:meta-llama/Llama-3.1-70B-Instruct",
"license:llama3.1",
"region:us",
"imatrix",
"conversational"
],
"likes": 2,
"downloads": 99,
"gated": false,
"private": false,
"last_modified": "2024-10-16T11:53:41.000Z",
"created_at": "2024-10-15T20:13:29.000Z",
"pipeline_tag": "text-generation",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "670ecce9be7efe81cfed76b3",
"id": "MarsupialAI/Llama-3.1-Nemotron-70B-Instruct_iMat_GGUF",
"modelId": "MarsupialAI/Llama-3.1-Nemotron-70B-Instruct_iMat_GGUF",
"sha": "de7e58cfc1736e78a11be342fc487f21cdd5fa85",
"createdAt": "2024-10-15T20:13:29.000Z",
"lastModified": "2024-10-16T11:53:41.000Z",
"author": "MarsupialAI",
"downloads": 99,
"likes": 2,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "transformers",
"siblings_count": 22
}