---
base_model:
- 152334H/miqu-1-70b-sf
- sophosympatheia/Midnight-Miqu-70B-v1.0
- alchemonaut/BoreanGale-70B
- NeverSleep/MiquMaid-v1-70B
exported_from: Undi95/MiquTotalMix-70B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About

weighted/imatrix quants of https://huggingface.co/Undi95/MiquTotalMix-70B

<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/MiquTotalMix-70B-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 |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 23.7 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.6 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 30.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 31.4 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.4 | slightly worse than Q4_K_S |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.9 |  |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 |  |
| [PART 1](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |


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

## 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 -->