--- base_model: meta-llama/Meta-Llama-3.1-8B-Instruct extra_gated_button_content: Submit extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_fields: Affiliation: text ? By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy : checkbox Country: country Date of birth: date_picker First Name: text Job title: options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other type: select Last Name: text geo: ip_location extra_gated_prompt: "### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT\nLlama 3.1 Version\ \ Release Date: July 23, 2024\n\"Agreement\" means the terms and conditions for\ \ use, reproduction, distribution and modification of the Llama Materials set forth\ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\ \ accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.\n\ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\ \ (if you are entering into this Agreement on such person or entity\u2019s behalf),\ \ of the age required under applicable laws, rules or regulations to provide legal\ \ consent and that has legal authority to bind your employer or such other person\ \ or entity if you are entering in this Agreement on their behalf.\n\"Llama 3.1\"\ \ means the foundational large language models and software and algorithms, including\ \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\ \ code, fine-tuning enabling code and other elements of the foregoing distributed\ \ by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means,\ \ collectively, Meta\u2019s proprietary Llama 3.1 and Documentation (and any portion\ \ thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms\ \ Ireland Limited (if you are located in or, if you are an entity, your principal\ \ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you\ \ are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\n\ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\ \ and royalty-free limited license under Meta\u2019s intellectual property or other\ \ rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\ \ copy, create derivative works of, and make modifications to the Llama Materials.\n\ b. Redistribution and Use.\ni. If you distribute or make available the Llama Materials\ \ (or any derivative works thereof), or a product or service (including another\ \ AI model) that contains any of them, you shall (A) provide a copy of this Agreement\ \ with any such Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\ \ on a related website, user interface, blogpost, about page, or product documentation.\ \ If you use the Llama Materials or any outputs or results of the Llama Materials\ \ to create, train, fine tune, or otherwise improve an AI model, which is distributed\ \ or made available, you shall also include \u201CLlama\u201D at the beginning of\ \ any such AI model name.\nii. If you receive Llama Materials, or any derivative\ \ works thereof, from a Licensee as part of an integrated end user product, then\ \ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\ \ copies of the Llama Materials that you distribute the following attribution notice\ \ within a \u201CNotice\u201D text file distributed as a part of such copies: \u201C\ Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright \xA9 Meta\ \ Platforms, Inc. All Rights Reserved.\u201D\niv. Your use of the Llama Materials\ \ must comply with applicable laws and regulations (including trade compliance laws\ \ and regulations) and adhere to the Acceptable Use Policy for the Llama Materials\ \ (available at https://llama.meta.com/llama3_1/use-policy), which is hereby incorporated\ \ by reference into this Agreement.\n2. Additional Commercial Terms. If, on the\ \ Llama 3.1 version release date, the monthly active users of the products or services\ \ made available by or for Licensee, or Licensee\u2019s affiliates, is greater than\ \ 700 million monthly active users in the preceding calendar month, you must request\ \ a license from Meta, which Meta may grant to you in its sole discretion, and you\ \ are not authorized to exercise any of the rights under this Agreement unless or\ \ until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty.\ \ UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS\ \ THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF ANY\ \ KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\ \ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\ \ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\ \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\ \ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\ \ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\ \ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\ \ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\ \ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\ \ any name or mark owned by or associated with the other or any of its affiliates,\ \ except as required for reasonable and customary use in describing and redistributing\ \ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\ \ a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required to\ \ comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019\ s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/\ \ ). All goodwill arising out of your use of the Mark will inure to the benefit\ \ of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives\ \ made by or for Meta, with respect to any derivative works and modifications of\ \ the Llama Materials that are made by you, as between you and Meta, you are and\ \ will be the owner of such derivative works and modifications.\nc. If you institute\ \ litigation or other proceedings against Meta or any entity (including a cross-claim\ \ or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs\ \ or results, or any portion of any of the foregoing, constitutes infringement of\ \ intellectual property or other rights owned or licensable by you, then any licenses\ \ granted to you under this Agreement shall terminate as of the date such litigation\ \ or claim is filed or instituted. You will indemnify and hold harmless Meta from\ \ and against any claim by any third party arising out of or related to your use\ \ or distribution of the Llama Materials.\n6. Term and Termination. The term of\ \ this Agreement will commence upon your acceptance of this Agreement or access\ \ to the Llama Materials and will continue in full force and effect until terminated\ \ in accordance with the terms and conditions herein. Meta may terminate this Agreement\ \ if you are in breach of any term or condition of this Agreement. Upon termination\ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\ \ and Jurisdiction. This Agreement will be governed and construed under the laws\ \ of the State of California without regard to choice of law principles, and the\ \ UN Convention on Contracts for the International Sale of Goods does not apply\ \ to this Agreement. The courts of California shall have exclusive jurisdiction\ \ of any dispute arising out of this Agreement.\n### Llama 3.1 Acceptable Use Policy\n\ Meta is committed to promoting safe and fair use of its tools and features, including\ \ Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy\ \ (\u201CPolicy\u201D). The most recent copy of this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy)\n\ #### Prohibited Uses\nWe want everyone to use Llama 3.1 safely and responsibly.\ \ You agree you will not use, or allow others to use, Llama 3.1 to:\n 1. Violate\ \ the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate,\ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\ \ illegal distribution of information or materials to minors, including obscene\ \ materials, or failure to employ legally required age-gating in connection with\ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\ \ other criminal activity\n 3. Engage in, promote, incite, or facilitate the\ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\ \ 4. Engage in, promote, incite, or facilitate discrimination or other unlawful\ \ or harmful conduct in the provision of employment, employment benefits, credit,\ \ housing, other economic benefits, or other essential goods and services\n 5.\ \ Engage in the unauthorized or unlicensed practice of any profession including,\ \ but not limited to, financial, legal, medical/health, or related professional\ \ practices\n 6. Collect, process, disclose, generate, or infer health, demographic,\ \ or other sensitive personal or private information about individuals without rights\ \ and consents required by applicable laws\n 7. Engage in or facilitate any action\ \ or generate any content that infringes, misappropriates, or otherwise violates\ \ any third-party rights, including the outputs or results of any products or services\ \ using the Llama Materials\n 8. Create, generate, or facilitate the creation\ \ of malicious code, malware, computer viruses or do anything else that could disable,\ \ overburden, interfere with or impair the proper working, integrity, operation\ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\ \ facilitate, or assist in the planning or development of activities that present\ \ a risk of death or bodily harm to individuals, including use of Llama 3.1 related\ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\ \ espionage, use for materials or activities that are subject to the International\ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\ \ content intended to incite or promote violence, abuse, or any infliction of bodily\ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\ \ of Llama 3.1 related to the following:\n 1. Generating, promoting, or furthering\ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\ \ or furthering defamatory content, including the creation of defamatory statements,\ \ images, or other content\n 3. Generating, promoting, or further distributing\ \ spam\n 4. Impersonating another individual without consent, authorization,\ \ or legal right\n 5. Representing that the use of Llama 3.1 or outputs are human-generated\n\ \ 6. Generating or facilitating false online engagement, including fake reviews\ \ and other means of fake online engagement\n4. Fail to appropriately disclose to\ \ end users any known dangers of your AI system\nPlease report any violation of\ \ this Policy, software \u201Cbug,\u201D or other problems that could lead to a\ \ violation of this Policy through one of the following means:\n * Reporting\ \ issues with the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)\n\ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com" inference: false language: - en - de - fr - it - pt - hi - es - th library_name: gguf license: llama3.1 pipeline_tag: text-generation quantized_by: legraphista tags: - facebook - meta - pytorch - llama - llama-3 - quantized - GGUF - quantization - imat - imatrix - static - 16bit - 8bit - 6bit - 5bit - 4bit - 3bit - 2bit - 1bit --- # Meta-Llama-3.1-8B-Instruct-IMat-GGUF _Llama.cpp imatrix quantization of meta-llama/Meta-Llama-3.1-8B-Instruct_ Original Model: [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) Original dtype: `BF16` (`bfloat16`) Quantized by: [https://github.com/ggerganov/llama.cpp/pull/8676](https://github.com/ggerganov/llama.cpp/pull/8676) IMatrix dataset: [here](https://gist.githubusercontent.com/bartowski1182/eb213dccb3571f863da82e99418f81e8/raw/b2869d80f5c16fd7082594248e80144677736635/calibration_datav3.txt) - [Files](#files) - [IMatrix](#imatrix) - [Common Quants](#common-quants) - [All Quants](#all-quants) - [Downloading using huggingface-cli](#downloading-using-huggingface-cli) - [Inference](#inference) - [Simple chat template](#simple-chat-template) - [Chat template with system prompt](#chat-template-with-system-prompt) - [Llama.cpp](#llama-cpp) - [FAQ](#faq) - [Why is the IMatrix not applied everywhere?](#why-is-the-imatrix-not-applied-everywhere) - [How do I merge a split GGUF?](#how-do-i-merge-a-split-gguf) --- ## Files ### IMatrix Status: ✅ Available Link: [here](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/imatrix.dat) ### Common Quants | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split | | -------- | ---------- | --------- | ------ | ------------ | -------- | | [Meta-Llama-3.1-8B-Instruct.Q8_0.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.54GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q6_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.60GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q4_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q4_K.gguf) | Q4_K | 4.92GB | ✅ Available | 🟢 IMatrix | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q3_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q3_K.gguf) | Q3_K | 4.02GB | ✅ Available | 🟢 IMatrix | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q2_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.18GB | ✅ Available | 🟢 IMatrix | 📦 No ### All Quants | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split | | -------- | ---------- | --------- | ------ | ------------ | -------- | | [Meta-Llama-3.1-8B-Instruct.BF16.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.BF16.gguf) | BF16 | 16.07GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.FP16.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.FP16.gguf) | F16 | 16.07GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q8_0.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.54GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q6_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.60GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q5_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q5_K.gguf) | Q5_K | 5.73GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q5_K_S.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.60GB | ✅ Available | ⚪ Static | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q4_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q4_K.gguf) | Q4_K | 4.92GB | ✅ Available | 🟢 IMatrix | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q4_K_S.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.69GB | ✅ Available | 🟢 IMatrix | 📦 No | Meta-Llama-3.1-8B-Instruct.IQ4_NL | IQ4_NL | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ4_XS | IQ4_XS | - | ⏳ Processing | 🟢 IMatrix | - | [Meta-Llama-3.1-8B-Instruct.Q3_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q3_K.gguf) | Q3_K | 4.02GB | ✅ Available | 🟢 IMatrix | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q3_K_L.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.32GB | ✅ Available | 🟢 IMatrix | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q3_K_S.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.66GB | ✅ Available | 🟢 IMatrix | 📦 No | Meta-Llama-3.1-8B-Instruct.IQ3_M | IQ3_M | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ3_S | IQ3_S | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ3_XS | IQ3_XS | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ3_XXS | IQ3_XXS | - | ⏳ Processing | 🟢 IMatrix | - | [Meta-Llama-3.1-8B-Instruct.Q2_K.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.18GB | ✅ Available | 🟢 IMatrix | 📦 No | [Meta-Llama-3.1-8B-Instruct.Q2_K_S.gguf](https://huggingface.co/legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct.Q2_K_S.gguf) | Q2_K_S | 2.99GB | ✅ Available | 🟢 IMatrix | 📦 No | Meta-Llama-3.1-8B-Instruct.IQ2_M | IQ2_M | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ2_S | IQ2_S | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ2_XS | IQ2_XS | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ2_XXS | IQ2_XXS | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ1_M | IQ1_M | - | ⏳ Processing | 🟢 IMatrix | - | Meta-Llama-3.1-8B-Instruct.IQ1_S | IQ1_S | - | ⏳ Processing | 🟢 IMatrix | - ## Downloading using huggingface-cli If you do not have hugginface-cli installed: ``` pip install -U "huggingface_hub[cli]" ``` Download the specific file you want: ``` huggingface-cli download legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF --include "Meta-Llama-3.1-8B-Instruct.Q8_0.gguf" --local-dir ./ ``` If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: ``` huggingface-cli download legraphista/Meta-Llama-3.1-8B-Instruct-IMat-GGUF --include "Meta-Llama-3.1-8B-Instruct.Q8_0/*" --local-dir ./ # see FAQ for merging GGUF's ``` --- ## Inference ### Simple chat template ``` <|begin_of_text|><|start_header_id|>user<|end_header_id|> {user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {assistant_response}<|eot_id|><|start_header_id|>user<|end_header_id|> {next_user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` ### Chat template with system prompt ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {assistant_response}<|eot_id|><|start_header_id|>user<|end_header_id|> {next_user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` ### Llama.cpp ``` llama.cpp/main -m Meta-Llama-3.1-8B-Instruct.Q8_0.gguf --color -i -p "prompt here (according to the chat template)" ``` --- ## FAQ ### Why is the IMatrix not applied everywhere? According to [this investigation](https://www.reddit.com/r/LocalLLaMA/comments/1993iro/ggufs_quants_can_punch_above_their_weights_now/), it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results). ### How do I merge a split GGUF? 1. Make sure you have `gguf-split` available - To get hold of `gguf-split`, navigate to https://github.com/ggerganov/llama.cpp/releases - Download the appropriate zip for your system from the latest release - Unzip the archive and you should be able to find `gguf-split` 2. Locate your GGUF chunks folder (ex: `Meta-Llama-3.1-8B-Instruct.Q8_0`) 3. Run `gguf-split --merge Meta-Llama-3.1-8B-Instruct.Q8_0/Meta-Llama-3.1-8B-Instruct.Q8_0-00001-of-XXXXX.gguf Meta-Llama-3.1-8B-Instruct.Q8_0.gguf` - Make sure to point `gguf-split` to the first chunk of the split. --- Got a suggestion? Ping me [@legraphista](https://x.com/legraphista)!