Model Intelligence Sheet
theprint/bohf-12b-moe-3a-gguf overview
BoHF (Best of Hugging Face) This is a highly experimental mixture of experts model, containing 4 expert models. The individual expert models are based on Llama 3.2 3B fine tunes that represent some of the most popular models of this kind.
Downloads
84
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
12 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| bohf-12b-moe-3a-f16.gguf | GGUF | F16 | 17.81 GB | Download |
| bohf-12b-moe-3a-iq4_xs.gguf | GGUF | IQ4_XS | 4.89 GB | Download |
| bohf-12b-moe-3a-q2_k.gguf | GGUF | Q2_K | 3.41 GB | Download |
| bohf-12b-moe-3a-q3_k_l.gguf | GGUF | Q3_K_L | 4.74 GB | Download |
| bohf-12b-moe-3a-q3_k_m.gguf | GGUF | Q3_K_M | 4.38 GB | Download |
| bohf-12b-moe-3a-q3_k_s.gguf | GGUF | Q3_K_S | 3.98 GB | Download |
| bohf-12b-moe-3a-q4_0.gguf | GGUF | — | 5.11 GB | Download |
| bohf-12b-moe-3a-q4_1.gguf | GGUF | — | 5.64 GB | Download |
| bohf-12b-moe-3a-q4_k_m.gguf | GGUF | Q4_K_M | 5.46 GB | Download |
| bohf-12b-moe-3a-q5_k_m.gguf | GGUF | Q5_K_M | 6.36 GB | Download |
| bohf-12b-moe-3a-q6_k.gguf | GGUF | Q6_K | 7.31 GB | Download |
| bohf-12b-moe-3a-q8_0.gguf | GGUF | — | 9.46 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "llama3.2",
"language": [
"en"
],
"base_model": [
"theprint/Bohf-12B-MoE-3A"
],
"tags": [
"moe"
],
"frontmatter": {
"license": "llama3.2",
"language": [
"en"
],
"base_model": [
"theprint/Bohf-12B-MoE-3A"
],
"tags": [
"moe"
]
},
"hero_image_url": "",
"summary": "# BoHF (Best of Hugging Face) This is a highly experimental mixture of experts model, containing 4 expert models. The individual expert models are based on Llama 3.2 3B fine tunes that represent some of the most popular models of this kind.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: llama3.2\nlanguage:\n- en\nbase_model:\n- theprint/Bohf-12B-MoE-3A\ntags:\n- moe\n---\n# BoHF (Best of Hugging Face)\n\n This is a highly experimental mixture of experts model, containing 4 expert models. The individual expert models are based on Llama 3.2 3B fine tunes that represent some of the most popular models of this kind.\n\n## Expert Source Models\n\nBig shout out to the makers of these original models, now serving as experts in BoHF!\n\n- [dphn/Dolphin3.0-Llama3.2-3B](https://huggingface.co/dphn/Dolphin3.0-Llama3.2-3B) for general inquiries.\n- [HenryShan/Llama-3.2-3B-GSM8K-CoT](https://huggingface.co/HenryShan/Llama-3.2-3B-GSM8K-CoT) for math.\n- [theprint/Llama-3.2-3B-VanRossum](https://huggingface.co/theprint/Llama-3.2-3B-VanRossum) for Python coding.\n- [ConicCat/Litbench-Creative-Writing-RM-3B](https://huggingface.co/ConicCat/Litbench-Creative-Writing-RM-3B) for creative writing.",
"related_quantizations": []
},
"tags": [
"gguf",
"moe",
"en",
"base_model:theprint/Bohf-12B-MoE-3A",
"base_model:quantized:theprint/Bohf-12B-MoE-3A",
"license:llama3.2",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 84,
"gated": false,
"private": false,
"last_modified": "2025-11-15T01:56:16.000Z",
"created_at": "2025-11-15T01:23:37.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6917d619b9d00158e2227585",
"id": "theprint/Bohf-12B-MoE-3A-GGUF",
"modelId": "theprint/Bohf-12B-MoE-3A-GGUF",
"sha": "a0ab1f1455f4bad47f31c8c52f6aec1569699da5",
"createdAt": "2025-11-15T01:23:37.000Z",
"lastModified": "2025-11-15T01:56:16.000Z",
"author": "theprint",
"downloads": 84,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 14
}