GraySoft
Projects Models About FAQ Contact Download guIDE →

lmstudio-community/meta-llama-3-120b-instruct-gguf Q5_K_M 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

lmstudio-community/meta-llama-3-120b-instruct-gguf overview

Comprehensive model page for lmstudio-community/meta-llama-3-120b-instruct-gguf

ggufmergemergekitlazymergekittext-generationbase_model:mlabonne/Meta-Llama-3-120B-Instructbase_model:quantized:mlabonne/Meta-Llama-3-120B-Instructlicense:otherendpoints_compatibleregion:usimatrixconversational
lmstudio-community/meta-llama-3-120b-instruct-gguf visual
Downloads
184
Likes
48
Pipeline
text-generation
Library
Visibility
Public
Access
Open

Repository Files & Downloads

31 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Meta-Llama-3-120B-Instruct-IQ1_M.gguf GGUF IQ1_M 26.54 GB Download
Meta-Llama-3-120B-Instruct-IQ1_S.gguf GGUF IQ1_S 24.24 GB Download
Meta-Llama-3-120B-Instruct-IQ2_M.gguf GGUF IQ2_M 38.47 GB Download
Meta-Llama-3-120B-Instruct-Q2_K.gguf GGUF Q2_K 42.00 GB Download
Meta-Llama-3-120B-Instruct-Q3_K_L-00001-of-00002.gguf GGUF Q3_K_L 29.93 GB Download
Meta-Llama-3-120B-Instruct-Q3_K_L-00002-of-00002.gguf GGUF Q3_K_L 29.68 GB Download
Meta-Llama-3-120B-Instruct-Q3_K_M-00001-of-00002.gguf GGUF Q3_K_M 29.95 GB Download
Meta-Llama-3-120B-Instruct-Q3_K_M-00002-of-00002.gguf GGUF Q3_K_M 24.83 GB Download
Meta-Llama-3-120B-Instruct-Q3_K_S-00001-of-00002.gguf GGUF Q3_K_S 29.94 GB Download
Meta-Llama-3-120B-Instruct-Q3_K_S-00002-of-00002.gguf GGUF Q3_K_S 19.24 GB Download
Meta-Llama-3-120B-Instruct-Q4_K_M-00001-of-00003.gguf GGUF Q4_K_M 29.99 GB Download
Meta-Llama-3-120B-Instruct-Q4_K_M-00002-of-00003.gguf GGUF Q4_K_M 29.91 GB Download
Meta-Llama-3-120B-Instruct-Q4_K_M-00003-of-00003.gguf GGUF Q4_K_M 8.31 GB Download
Meta-Llama-3-120B-Instruct-Q4_K_S-00001-of-00003.gguf GGUF Q4_K_S 29.99 GB Download
Meta-Llama-3-120B-Instruct-Q4_K_S-00002-of-00003.gguf GGUF Q4_K_S 30.00 GB Download
Meta-Llama-3-120B-Instruct-Q4_K_S-00003-of-00003.gguf GGUF Q4_K_S 4.60 GB Download
Meta-Llama-3-120B-Instruct-Q5_K_M-00001-of-00003.gguf GGUF Q5_K_M 29.92 GB Download
Meta-Llama-3-120B-Instruct-Q5_K_M-00002-of-00003.gguf GGUF Q5_K_M 29.98 GB Download
Meta-Llama-3-120B-Instruct-Q5_K_M-00003-of-00003.gguf GGUF Q5_K_M 20.39 GB Download
Meta-Llama-3-120B-Instruct-Q5_K_S-00001-of-00003.gguf GGUF Q5_K_S 29.88 GB Download
Meta-Llama-3-120B-Instruct-Q5_K_S-00002-of-00003.gguf GGUF Q5_K_S 29.94 GB Download
Meta-Llama-3-120B-Instruct-Q5_K_S-00003-of-00003.gguf GGUF Q5_K_S 18.38 GB Download
Meta-Llama-3-120B-Instruct-Q6_K-00001-of-00004.gguf GGUF Q6_K 29.97 GB Download
Meta-Llama-3-120B-Instruct-Q6_K-00002-of-00004.gguf GGUF Q6_K 29.89 GB Download
Meta-Llama-3-120B-Instruct-Q6_K-00003-of-00004.gguf GGUF Q6_K 30.00 GB Download
Meta-Llama-3-120B-Instruct-Q6_K-00004-of-00004.gguf GGUF Q6_K 3.28 GB Download
Meta-Llama-3-120B-Instruct-Q8_0-00001-of-00005.gguf GGUF 29.88 GB Download
Meta-Llama-3-120B-Instruct-Q8_0-00002-of-00005.gguf GGUF 29.88 GB Download
Meta-Llama-3-120B-Instruct-Q8_0-00003-of-00005.gguf GGUF 29.93 GB Download
Meta-Llama-3-120B-Instruct-Q8_0-00004-of-00005.gguf GGUF 29.95 GB Download
Meta-Llama-3-120B-Instruct-Q8_0-00005-of-00005.gguf GGUF 1011.59 MB Download

Model Details Live

Model Slug
lmstudio-community/meta-llama-3-120b-instruct-gguf
Author
lmstudio-community
Pipeline Task
text-generation
Library
Created
2024-05-09
Last Modified
2024-05-09
Gated
No
Private
No
HF SHA
cef120ff442701448a262dc49f9d2573fc2c7714
License
other
Language
Unknown
Base Model
mlabonne/Meta-Llama-3-120B-Instruct

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "other",
    "tags": [
      "merge",
      "mergekit",
      "lazymergekit"
    ],
    "base_model": [
      "mlabonne/Meta-Llama-3-120B-Instruct"
    ],
    "quantized_by": "bartowski",
    "pipeline_tag": "text-generation",
    "lm_studio": {
      "param_count": "120b",
      "use_case": "general",
      "release_date": "01-05-2024",
      "model_creator": "mlabonne",
      "prompt_template": "Llama 3",
      "system_prompt": "You are a helpful AI assistant.",
      "base_model": "llama",
      "original_repo": "mlabonne/Meta-Llama-3-120B-Instruct"
    },
    "frontmatter": {
      "license": "other",
      "tags": [
        "merge",
        "mergekit",
        "lazymergekit"
      ],
      "base_model": [
        "mlabonne/Meta-Llama-3-120B-Instruct"
      ],
      "quantized_by": "bartowski",
      "pipeline_tag": "text-generation",
      "lm_studio": []
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\ntags:\n- merge\n- mergekit\n- lazymergekit\nbase_model:\n- mlabonne/Meta-Llama-3-120B-Instruct\nquantized_by: bartowski\npipeline_tag: text-generation\nlm_studio:\n  param_count: 120b\n  use_case: general\n  release_date: 01-05-2024\n  model_creator: mlabonne\n  prompt_template: Llama 3\n  system_prompt: You are a helpful AI assistant.\n  base_model: llama\n  original_repo: mlabonne/Meta-Llama-3-120B-Instruct\n---\n\n## 💫 Community Model> Llama 3 120B Instruct by Maxime Labonne\n\n*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.\n\n**Model creator:** [mlabonne](https://huggingface.co/mlabonne)<br>\n**Original model**: [Meta-Llama-3-120B-Instruct](https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct)<br>\n**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2794](https://github.com/ggerganov/llama.cpp/releases/tag/b2794)<br>\n\n## Model Summary:\nMeta-Llama-3-120B-Instruct is a meta-llama/Meta-Llama-3-70B-Instruct self-merge made with MergeKit.<br>\nUsing self-merging expands the capabilities of a model without additional training costs.<br>\n\n\n## Prompt Template:\n\nChoose the 'Llama 3' preset in your LM Studio. \n\nUnder the hood, the model will see a prompt that's formatted like so:\n\n```\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n```\n\n## Technical Details\n\nView the original model page for technical details and examples. There aren't a lot of extra details besides the merge configuration.\n\n## Special thanks\n\n🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.\n\n🙏 Special thanks to [Kalomaze](https://github.com/kalomaze) for his dataset (linked [here](https://github.com/ggerganov/llama.cpp/discussions/5263))\n\n## Disclaimers\n\nLM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model.  You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models.  LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "merge",
    "mergekit",
    "lazymergekit",
    "text-generation",
    "base_model:mlabonne/Meta-Llama-3-120B-Instruct",
    "base_model:quantized:mlabonne/Meta-Llama-3-120B-Instruct",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 48,
  "downloads": 184,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-09T16:19:07.000Z",
  "created_at": "2024-05-09T03:48:46.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "663c479ea14bfb0a2d9d19bc",
  "id": "lmstudio-community/Meta-Llama-3-120B-Instruct-GGUF",
  "modelId": "lmstudio-community/Meta-Llama-3-120B-Instruct-GGUF",
  "sha": "cef120ff442701448a262dc49f9d2573fc2c7714",
  "createdAt": "2024-05-09T03:48:46.000Z",
  "lastModified": "2024-05-09T16:19:07.000Z",
  "author": "lmstudio-community",
  "downloads": 184,
  "likes": 48,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 35
}