Model Intelligence Sheet
richarderkhov/finnish-nlp_-_ahma-7b-gguf overview
Comprehensive model page for richarderkhov/finnish-nlp-ahma-7b-gguf
Downloads
150
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
22 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Ahma-7B.IQ3_M.gguf | GGUF | IQ3_M | 3.06 GB | Download |
| Ahma-7B.IQ3_S.gguf | GGUF | IQ3_S | 2.90 GB | Download |
| Ahma-7B.IQ3_XS.gguf | GGUF | IQ3_XS | 2.76 GB | Download |
| Ahma-7B.IQ4_NL.gguf | GGUF | IQ4_NL | 3.76 GB | Download |
| Ahma-7B.IQ4_XS.gguf | GGUF | IQ4_XS | 3.56 GB | Download |
| Ahma-7B.Q2_K.gguf | GGUF | Q2_K | 2.50 GB | Download |
| Ahma-7B.Q3_K.gguf | GGUF | Q3_K | 3.23 GB | Download |
| Ahma-7B.Q3_K_L.gguf | GGUF | Q3_K_L | 3.50 GB | Download |
| Ahma-7B.Q3_K_M.gguf | GGUF | Q3_K_M | 3.23 GB | Download |
| Ahma-7B.Q3_K_S.gguf | GGUF | Q3_K_S | 2.90 GB | Download |
| Ahma-7B.Q4_0.gguf | GGUF | — | 3.73 GB | Download |
| Ahma-7B.Q4_1.gguf | GGUF | — | 4.13 GB | Download |
| Ahma-7B.Q4_K.gguf | GGUF | Q4_K | 3.97 GB | Download |
| Ahma-7B.Q4_K_M.gguf | GGUF | Q4_K_M | 3.97 GB | Download |
| Ahma-7B.Q4_K_S.gguf | GGUF | Q4_K_S | 3.76 GB | Download |
| Ahma-7B.Q5_0.gguf | GGUF | — | 4.52 GB | Download |
| Ahma-7B.Q5_1.gguf | GGUF | — | 4.91 GB | Download |
| Ahma-7B.Q5_K.gguf | GGUF | Q5_K | 4.64 GB | Download |
| Ahma-7B.Q5_K_M.gguf | GGUF | Q5_K_M | 4.64 GB | Download |
| Ahma-7B.Q5_K_S.gguf | GGUF | Q5_K_S | 4.52 GB | Download |
| Ahma-7B.Q6_K.gguf | GGUF | Q6_K | 5.35 GB | Download |
| Ahma-7B.Q8_0.gguf | GGUF | — | 6.93 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nAhma-7B - GGUF\n- Model creator: https://huggingface.co/Finnish-NLP/\n- Original model: https://huggingface.co/Finnish-NLP/Ahma-7B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Ahma-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q2_K.gguf) | Q2_K | 2.5GB |\n| [Ahma-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.IQ3_XS.gguf) | IQ3_XS | 2.76GB |\n| [Ahma-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.IQ3_S.gguf) | IQ3_S | 2.9GB |\n| [Ahma-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q3_K_S.gguf) | Q3_K_S | 2.9GB |\n| [Ahma-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Ahma-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q3_K.gguf) | Q3_K | 3.23GB |\n| [Ahma-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q3_K_M.gguf) | Q3_K_M | 3.23GB |\n| [Ahma-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q3_K_L.gguf) | Q3_K_L | 3.5GB |\n| [Ahma-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.IQ4_XS.gguf) | IQ4_XS | 3.56GB |\n| [Ahma-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q4_0.gguf) | Q4_0 | 3.73GB |\n| [Ahma-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.IQ4_NL.gguf) | IQ4_NL | 3.76GB |\n| [Ahma-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q4_K_S.gguf) | Q4_K_S | 3.76GB |\n| [Ahma-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q4_K.gguf) | Q4_K | 3.97GB |\n| [Ahma-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q4_K_M.gguf) | Q4_K_M | 3.97GB |\n| [Ahma-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q4_1.gguf) | Q4_1 | 4.13GB |\n| [Ahma-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q5_0.gguf) | Q5_0 | 4.52GB |\n| [Ahma-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q5_K_S.gguf) | Q5_K_S | 4.52GB |\n| [Ahma-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q5_K.gguf) | Q5_K | 4.64GB |\n| [Ahma-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q5_K_M.gguf) | Q5_K_M | 4.64GB |\n| [Ahma-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q5_1.gguf) | Q5_1 | 4.91GB |\n| [Ahma-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q6_K.gguf) | Q6_K | 5.35GB |\n| [Ahma-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf/blob/main/Ahma-7B.Q8_0.gguf) | Q8_0 | 6.93GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- fi\nlicense: apache-2.0\ntags:\n- finnish\n- llama\ninference: false\npipeline_tag: text-generation\n\n---\n\n# TBA\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 150,
"gated": false,
"private": false,
"last_modified": "2024-09-07T20:38:03.000Z",
"created_at": "2024-09-07T14:30:26.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "66dc6382946bce6c94d85198",
"id": "RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf",
"modelId": "RichardErkhov/Finnish-NLP_-_Ahma-7B-gguf",
"sha": "c7b46e3f96a071673492f0598c0897276bbf81ce",
"createdAt": "2024-09-07T14:30:26.000Z",
"lastModified": "2024-09-07T20:38:03.000Z",
"author": "RichardErkhov",
"downloads": 150,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}