|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
language: |
|
- en |
|
- de |
|
- fr |
|
- it |
|
- pt |
|
- hi |
|
- es |
|
- th |
|
license: llama3.1 |
|
pipeline_tag: text-generation |
|
tags: |
|
- facebook |
|
- meta |
|
- pytorch |
|
- llama |
|
- llama-3 |
|
quantized_by: bartowski |
|
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’s 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’s 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’s 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.\nb.\ |
|
\ 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 “Built with Llama”\ |
|
\ 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 “Llama” 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\ |
|
\ “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed\ |
|
\ under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights\ |
|
\ Reserved.”\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’s\ |
|
\ 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 “AS IS”\ |
|
\ 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.\n4. 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.\n5. 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 “Llama” (the\ |
|
\ “Mark”) solely as required to comply with the last sentence of Section 1.b.i.\ |
|
\ You will comply with Meta’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’s 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\ |
|
\ (“Policy”). 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’ 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 “bug,” 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" |
|
extra_gated_fields: |
|
First Name: text |
|
Last Name: text |
|
Date of birth: date_picker |
|
Country: country |
|
Affiliation: text |
|
Job title: |
|
type: select |
|
options: |
|
- Student |
|
- Research Graduate |
|
- AI researcher |
|
- AI developer/engineer |
|
- Reporter |
|
- Other |
|
geo: ip_location |
|
? 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 |
|
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_button_content: Submit |
|
--- |
|
|
|
## Llamacpp imatrix Quantizations of Meta-Llama-3.1-8B-Instruct |
|
|
|
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3441">b3441</a> for quantization. |
|
|
|
Original model: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct |
|
|
|
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) |
|
|
|
Run them in [LM Studio](https://lmstudio.ai/) |
|
|
|
## Prompt format |
|
|
|
``` |
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|> |
|
|
|
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> |
|
|
|
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> |
|
|
|
|
|
``` |
|
|
|
## Download a file (not the whole branch) from below: |
|
|
|
| Filename | Quant type | File Size | Split | Description | |
|
| -------- | ---------- | --------- | ----- | ----------- | |
|
| [Meta-Llama-3.1-8B-Instruct-f32.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-f32.gguf) | f32 | 32.13GB | false | Full F32 weights. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for must use cases, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. | |
|
| [Meta-Llama-3.1-8B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. | |
|
| [Meta-Llama-3.1-8B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | |
|
| [Meta-Llama-3.1-8B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. | |
|
| [Meta-Llama-3.1-8B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-IQ2_M.gguf) | IQ2_M | 2.95GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | |
|
|
|
## Credits |
|
|
|
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset |
|
|
|
Thank you ZeroWw for the inspiration to experiment with embed/output |
|
|
|
## Downloading using huggingface-cli |
|
|
|
First, make sure you have hugginface-cli installed: |
|
|
|
``` |
|
pip install -U "huggingface_hub[cli]" |
|
``` |
|
|
|
Then, you can target the specific file you want: |
|
|
|
``` |
|
huggingface-cli download bartowski/Meta-Llama-3.1-8B-Instruct-GGUF --include "Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf" --local-dir ./ |
|
``` |
|
|
|
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: |
|
|
|
``` |
|
huggingface-cli download bartowski/Meta-Llama-3.1-8B-Instruct-GGUF --include "Meta-Llama-3.1-8B-Instruct-Q8_0.gguf/*" --local-dir Meta-Llama-3.1-8B-Instruct-Q8_0 |
|
``` |
|
|
|
You can either specify a new local-dir (Meta-Llama-3.1-8B-Instruct-Q8_0) or download them all in place (./) |
|
|
|
## Which file should I choose? |
|
|
|
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) |
|
|
|
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. |
|
|
|
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. |
|
|
|
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. |
|
|
|
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. |
|
|
|
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. |
|
|
|
If you want to get more into the weeds, you can check out this extremely useful feature chart: |
|
|
|
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) |
|
|
|
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. |
|
|
|
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. |
|
|
|
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. |
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
|
|
|
|
