---
base_model: mgoin/Nemotron-4-340B-Instruct-hf
language:
- en
library_name: transformers
license: other
license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
license_name: nvidia-open-model-license
quantized_by: mradermacher
tags:
- vllm
---
## About

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type:  -->
<!-- ### tags:  -->
weighted/imatrix quants of https://huggingface.co/mgoin/Nemotron-4-340B-Instruct-hf

<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-GGUF
## Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.

## Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_S.gguf.part2of2) | i1-IQ1_S | 74.9 | for the desperate |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_M.gguf.part2of2) | i1-IQ1_M | 81.5 | mostly desperate |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_XXS.gguf.part2of2) | i1-IQ2_XXS | 92.4 |  |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_XS.gguf.part3of3) | i1-IQ2_XS | 102.2 |  |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part3of3) | i1-IQ2_S | 108.9 |  |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_M.gguf.part3of3) | i1-IQ2_M | 117.6 |  |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q2_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q2_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q2_K.gguf.part3of3) | i1-Q2_K | 131.6 | IQ3_XXS probably better |
| [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part4of4) | i1-Q4_K_S | 195.2 | optimal size/speed/quality |

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

## FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

## Thanks

I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

<!-- end -->