---
base_model: ehristoforu/Gistral-16B
datasets:
- HuggingFaceH4/grok-conversation-harmless
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized_fixed
- HuggingFaceH4/cai-conversation-harmless
- meta-math/MetaMathQA
- emozilla/yarn-train-tokenized-16k-mistral
- snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
- microsoft/orca-math-word-problems-200k
- m-a-p/Code-Feedback
- teknium/openhermes
- lksy/ru_instruct_gpt4
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
- IlyaGusev/oasst1_ru_main_branch
language:
- en
- fr
- ru
- de
- ja
- ko
- zh
- it
- uk
- multilingual
- code
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- mistral
- gistral
- gistral-16b
- multilingual
- code
- 128k
- metamath
- grok-1
- anthropic
- openhermes
- instruct
- merge
---
## About

<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type:  -->
<!-- ### vocab_type:  -->
static quants of https://huggingface.co/ehristoforu/Gistral-16B

<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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 |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q2_K.gguf) | Q2_K | 6.4 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.IQ3_XS.gguf) | IQ3_XS | 7.0 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q3_K_S.gguf) | Q3_K_S | 7.4 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.IQ3_S.gguf) | IQ3_S | 7.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.IQ3_M.gguf) | IQ3_M | 7.7 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q3_K_M.gguf) | Q3_K_M | 8.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q3_K_L.gguf) | Q3_K_L | 9.0 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.IQ4_XS.gguf) | IQ4_XS | 9.2 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q4_K_S.gguf) | Q4_K_S | 9.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q4_K_M.gguf) | Q4_K_M | 10.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q5_K_S.gguf) | Q5_K_S | 11.7 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q5_K_M.gguf) | Q5_K_M | 12.0 |  |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q6_K.gguf) | Q6_K | 13.9 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Gistral-16B-GGUF/resolve/main/Gistral-16B.Q8_0.gguf) | Q8_0 | 18.0 | fast, best 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 -->