adamo1139/magnum-v2-4b-gguf-lowctx IQ3_XXS 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
adamo1139/magnum-v2-4b-gguf-lowctx overview
https://github.com/ggerganov/llama.cpp/pull/9141 PR to get long context support for this model in llama.cpp has been merged, so those quants no longer need to be used provided you have a newly compiled llama.cpp build. You can find official long ctx quants here
Downloads
89
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
18 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| magnum-v2-4b-lowctx-Q2_K.gguf | GGUF | Q2_K | 1.71 GB | Download |
| magnum-v2-4b-lowctx-Q3_K_M.gguf | GGUF | Q3_K_M | 2.14 GB | Download |
| magnum-v2-4b-lowctx-Q4_0.gguf | GGUF | — | 2.47 GB | Download |
| magnum-v2-4b-lowctx-Q4_0_4_4.gguf | GGUF | — | 2.47 GB | Download |
| magnum-v2-4b-lowctx-Q4_0_4_8.gguf | GGUF | — | 2.47 GB | Download |
| magnum-v2-4b-lowctx-Q4_0_8_8.gguf | GGUF | — | 2.47 GB | Download |
| magnum-v2-4b-lowctx-Q4_K_M.gguf | GGUF | Q4_K_M | 2.59 GB | Download |
| magnum-v2-4b-lowctx-Q4_K_S.gguf | GGUF | Q4_K_S | 2.48 GB | Download |
| magnum-v2-4b-lowctx-Q5_K_M.gguf | GGUF | Q5_K_M | 3.01 GB | Download |
| magnum-v2-4b-lowctx-iMat-IQ3_M.gguf | GGUF | IQ3_M | 2.03 GB | Download |
| magnum-v2-4b-lowctx-iMat-IQ3_S.gguf | GGUF | IQ3_S | 1.97 GB | Download |
| magnum-v2-4b-lowctx-iMat-IQ3_XS.gguf | GGUF | IQ3_XS | 1.89 GB | Download |
| magnum-v2-4b-lowctx-iMat-IQ3_XXS.gguf | GGUF | IQ3_XXS | 1.75 GB | Download |
| magnum-v2-4b-lowctx-iMat-IQ4_NL.gguf | GGUF | IQ4_NL | 2.48 GB | Download |
| magnum-v2-4b-lowctx-iMat-IQ4_XS.gguf | GGUF | IQ4_XS | 2.36 GB | Download |
| magnum-v2-4b-lowctx-iMat-Q2_K_S.gguf | GGUF | Q2_K_S | 1.61 GB | Download |
| magnum-v2-4b-lowctx-iMat-Q3_K_L.gguf | GGUF | Q3_K_L | 2.30 GB | Download |
| magnum-v2-4b-lowctx-iMat-Q6_K.gguf | GGUF | Q6_K | 3.46 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "https://github.com/ggerganov/llama.cpp/pull/9141 PR to get long context support for this model in llama.cpp has been merged, so those quants no longer need to be used provided you have a newly compiled llama.cpp build. You can find official long ctx quants here",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "\nhttps://github.com/ggerganov/llama.cpp/pull/9141\n\nPR to get long context support for this model in llama.cpp has been merged, so those quants no longer need to be used provided you have a newly compiled llama.cpp build.\nYou can find official long ctx quants [here](https://huggingface.co/anthracite-org/magnum-v2-4b-gguf) \n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 0,
"downloads": 89,
"gated": false,
"private": false,
"last_modified": "2024-08-27T07:22:27.000Z",
"created_at": "2024-08-23T21:32:48.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "66c900006058eb4e6bf38035",
"id": "adamo1139/magnum-v2-4b-gguf-lowctx",
"modelId": "adamo1139/magnum-v2-4b-gguf-lowctx",
"sha": "7831011db84d22f559748c527e3d972fb129acaf",
"createdAt": "2024-08-23T21:32:48.000Z",
"lastModified": "2024-08-27T07:22:27.000Z",
"author": "adamo1139",
"downloads": 89,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 20
}