artefact2/mixtral-8x7b-instruct-v0.1-gguf Q6_K 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.
artefact2/mixtral-8x7b-instruct-v0.1-gguf overview
These are GGUF quantized versions of mistralai/Mixtral-8x7B-Instruct-v0.1. The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw. Some model files above 50GB are split into smaller files. To concatenate them, use the cat command (on Windows, use PowerShell): cat foo-Q6K.gguf.* foo-Q6K.gguf What quant do I need? See https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 Quant requests? Just open a discussion in the community tabs.
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1-IQ2_M.gguf | GGUF | IQ2_M | 14.43 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ2_S.gguf | GGUF | IQ2_S | 13.16 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ2_XS.gguf | GGUF | IQ2_XS | 12.97 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 11.69 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ3_M.gguf | GGUF | IQ3_M | 19.96 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ3_S.gguf | GGUF | IQ3_S | 19.03 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ3_XS.gguf | GGUF | IQ3_XS | 17.96 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 16.99 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-IQ4_XS.gguf | GGUF | IQ4_XS | 23.36 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-Q4_K_M.gguf | GGUF | Q4_K_M | 26.49 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-Q4_K_S.gguf | GGUF | Q4_K_S | 24.91 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-Q5_K_M.gguf | GGUF | Q5_K_M | 30.95 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-Q5_K_S.gguf | GGUF | Q5_K_S | 30.02 GB | Download |
| Mixtral-8x7B-Instruct-v0.1-Q6_K.gguf | GGUF | Q6_K | 35.74 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"language": [
"en"
],
"license": "apache-2.0",
"frontmatter": {
"language": [
"en"
],
"license": "apache-2.0"
},
"hero_image_url": "",
"summary": "These are GGUF quantized versions of mistralai/Mixtral-8x7B-Instruct-v0.1. The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw. Some model files above 50GB are split into smaller files. To concatenate them, use the cat command (on Windows, use PowerShell): cat foo-Q6_K.gguf.* > foo-Q6_K.gguf * What quant do I need? See https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 * Quant requests? Just open a discussion in the community tabs.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlanguage:\n- en\nlicense: apache-2.0\n---\n\nThese are GGUF quantized versions of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1).\n\nThe importance matrix was trained for 100K tokens (200 batches of 512 tokens) using `wiki.train.raw`.\n\nSome model files above 50GB are split into smaller files. To concatenate them, use the `cat` command (on Windows, use PowerShell): `cat foo-Q6_K.gguf.* > foo-Q6_K.gguf`\n\n* What quant do I need? See https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n* Quant requests? Just open a discussion in the community tabs.",
"related_quantizations": []
},
"tags": [
"gguf",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 9,
"downloads": 189,
"gated": false,
"private": false,
"last_modified": "2024-03-11T18:13:07.000Z",
"created_at": "2024-02-27T02:10:06.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "65dd447e538de8896038833c",
"id": "Artefact2/Mixtral-8x7B-Instruct-v0.1-GGUF",
"modelId": "Artefact2/Mixtral-8x7B-Instruct-v0.1-GGUF",
"sha": "b135dcb05c18ba9a8fe2ee388e92d1abd9e29fed",
"createdAt": "2024-02-27T02:10:06.000Z",
"lastModified": "2024-03-11T18:13:07.000Z",
"author": "Artefact2",
"downloads": 189,
"likes": 9,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 17
}