---
quantized_by: bartowski
pipeline_tag: text-generation
license: other
tags:
- facebook
- meta
- llama
- llama-4
base_model: meta-llama/Llama-4-Scout-17B-16E-Instruct
extra_gated_prompt: '**LLAMA 4 COMMUNITY LICENSE AGREEMENT**

  Llama 4 Version Effective Date: April 5, 2025

  "**Agreement**" means the terms and conditions for use, reproduction, distribution
  and modification of the Llama Materials set forth herein.

  "**Documentation**" means the specifications, manuals and documentation accompanying
  Llama 4 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/overview).

  "**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.

  "**Llama 4**" 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://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).

  "**Llama Materials**" means, collectively, Meta’s proprietary Llama 4 and Documentation
  (and any portion thereof) made available under this Agreement.

  "**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). 

  By clicking "I Accept" below or by using or distributing any portion or element
  of the Llama Materials, you agree to be bound by this Agreement.

  1\. **License Rights and Redistribution**.

  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.  

  b. Redistribution and Use.  

  i. 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.

  ii. 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. 

  iii. 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 4 is licensed under the Llama 4 Community License, Copyright
  © Meta Platforms, Inc. All Rights Reserved."

  iv. 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://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy)),
  which is hereby incorporated by reference into this Agreement.        2\. **Additional
  Commercial Terms**. If, on the Llama 4 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.

  3**. 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.

  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.

  5\. **Intellectual Property**.

  a. 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/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/).
  All goodwill arising out of your use of the Mark will inure to the benefit of Meta.

  b. 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.

  c. 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 4 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.

  6\. **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. 

  7\. **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.'
extra_gated_button_content: Submit
license_name: llama4
extra_gated_heading: Please be sure to provide your full legal name, date of birth,
  and full organization name with all corporate identifiers. Avoid the use of acronyms
  and special characters. Failure to follow these instructions may prevent you from
  accessing this model and others on Hugging Face. You will not have the ability to
  edit this form after submission, so please ensure all information is accurate.
base_model_relation: quantized
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/).
language:
- ar
- de
- en
- es
- fr
- hi
- id
- it
- pt
- th
- tl
- vi
---

## Llamacpp imatrix Quantizations of Llama-4-Scout-17B-16E-Instruct by meta-llama

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5074">b5074</a> with my PR changes from [here](https://github.com/ggml-org/llama.cpp/pull/12727) for quantization.

Original model: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-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/)

Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project

## Prompt format

```
<|begin_of_text|><|header_start|>system<|header_end|>

{system_prompt}<|eot|><|header_start|>user<|header_end|>

{prompt}<|eot|><|header_start|>assistant<|header_end|>
```

## Download a file (not the whole branch) from below:

| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Llama-4-Scout-17B-16E-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q8_0) | Q8_0 | 113.40GB | true | Extremely high quality, generally unneeded but max available quant. |
| [Llama-4-Scout-17B-16E-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q6_K_L) | Q6_K_L | 89.26GB | true | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Llama-4-Scout-17B-16E-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q5_K_L) | Q5_K_L | 79.32GB | true | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-4-Scout-17B-16E-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q4_1) | Q4_1 | 69.10GB | true | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Llama-4-Scout-17B-16E-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q4_K_L) | Q4_K_L | 68.31GB | true | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-4-Scout-17B-16E-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q4_K_M) | Q4_K_M | 67.55GB | true | Good quality, default size for most use cases, *recommended*. |
| [Llama-4-Scout-17B-16E-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q4_0) | Q4_0 | 63.05GB | true | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Llama-4-Scout-17B-16E-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ4_NL) | IQ4_NL | 62.99GB | true | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Llama-4-Scout-17B-16E-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ4_XS) | IQ4_XS | 59.89GB | true | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-4-Scout-17B-16E-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_XL) | Q3_K_XL | 58.70GB | true | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Llama-4-Scout-17B-16E-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_L) | Q3_K_L | 57.80GB | true | Lower quality but usable, good for low RAM availability. |
| [Llama-4-Scout-17B-16E-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_M) | Q3_K_M | 54.32GB | true | Low quality. |
| [Llama-4-Scout-17B-16E-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ3_M) | IQ3_M | 50.32GB | true | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-4-Scout-17B-16E-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q3_K_S.gguf) | Q3_K_S | 49.75GB | false | Low quality, not recommended. |
| [Llama-4-Scout-17B-16E-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ3_XS.gguf) | IQ3_XS | 47.45GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-4-Scout-17B-16E-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 44.96GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Llama-4-Scout-17B-16E-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q2_K_L.gguf) | Q2_K_L | 44.00GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Llama-4-Scout-17B-16E-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-Q2_K.gguf) | Q2_K | 42.99GB | false | Very low quality but surprisingly usable. |
| [Llama-4-Scout-17B-16E-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ2_M.gguf) | IQ2_M | 37.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Llama-4-Scout-17B-16E-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ2_S.gguf) | IQ2_S | 34.34GB | false | Low quality, uses SOTA techniques to be usable. |
| [Llama-4-Scout-17B-16E-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ2_XS.gguf) | IQ2_XS | 32.94GB | false | Low quality, uses SOTA techniques to be usable. |
| [Llama-4-Scout-17B-16E-Instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ2_XXS.gguf) | IQ2_XXS | 30.17GB | false | Very low quality, uses SOTA techniques to be usable. |
| [Llama-4-Scout-17B-16E-Instruct-IQ1_M.gguf](https://huggingface.co/bartowski/meta-llama_Llama-4-Scout-17B-16E-Instruct-GGUF/blob/main/meta-llama_Llama-4-Scout-17B-16E-Instruct-IQ1_M.gguf) | IQ1_M | 26.32GB | false | Extremely low quality, *not* recommended. |

## Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

## Downloading using huggingface-cli

<details>
  <summary>Click to view download instructions</summary>

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_Llama-4-Scout-17B-16E-Instruct-GGUF --include "meta-llama_Llama-4-Scout-17B-16E-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_Llama-4-Scout-17B-16E-Instruct-GGUF --include "meta-llama_Llama-4-Scout-17B-16E-Instruct-Q8_0/*" --local-dir ./
```

You can either specify a new local-dir (meta-llama_Llama-4-Scout-17B-16E-Instruct-Q8_0) or download them all in place (./)

</details>

## ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

<details>
  <summary>Click to view Q4_0_X_X information (deprecated</summary>

I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.

<details>
  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>

| model                          |       size |     params | backend    | threads |          test |                  t/s |  % (vs Q4_0)  |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         pp512 |        204.03 ± 1.03 |          100% |
| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp1024 |        282.92 ± 0.19 |          100% |
| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp2048 |        259.49 ± 0.44 |          100% |
| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg128 |         39.12 ± 0.27 |          100% |
| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg256 |         39.31 ± 0.69 |          100% |
| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg512 |         40.52 ± 0.03 |          100% |
| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         pp512 |        301.02 ± 1.74 |          147% |
| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp1024 |        287.23 ± 0.20 |          101% |
| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp2048 |        262.77 ± 1.81 |          101% |
| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg128 |         18.80 ± 0.99 |           48% |
| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg256 |         24.46 ± 3.04 |           83% |
| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg512 |         36.32 ± 3.59 |           90% |
| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         pp512 |        271.71 ± 3.53 |          133% |
| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp1024 |       279.86 ± 45.63 |          100% |
| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp2048 |        320.77 ± 5.00 |          124% |
| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg128 |         43.51 ± 0.05 |          111% |
| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg256 |         43.35 ± 0.09 |          110% |
| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg512 |         42.60 ± 0.31 |          105% |

Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation

</details>

</details>

## Which file should I choose?

<details>
  <summary>Click here for details</summary>

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, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

</details>

## 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.

Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski