Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


UnFimbulvetr-20B - GGUF
- Model creator: https://huggingface.co/KaraKaraWitch/
- Original model: https://huggingface.co/KaraKaraWitch/UnFimbulvetr-20B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [UnFimbulvetr-20B.Q2_K.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q2_K.gguf) | Q2_K | 6.87GB |
| [UnFimbulvetr-20B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q3_K_S.gguf) | Q3_K_S | 8.01GB |
| [UnFimbulvetr-20B.Q3_K.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q3_K.gguf) | Q3_K | 8.93GB |
| [UnFimbulvetr-20B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q3_K_M.gguf) | Q3_K_M | 8.93GB |
| [UnFimbulvetr-20B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q3_K_L.gguf) | Q3_K_L | 9.73GB |
| [UnFimbulvetr-20B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.IQ4_XS.gguf) | IQ4_XS | 10.03GB |
| [UnFimbulvetr-20B.Q4_0.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q4_0.gguf) | Q4_0 | 10.46GB |
| [UnFimbulvetr-20B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.IQ4_NL.gguf) | IQ4_NL | 10.57GB |
| [UnFimbulvetr-20B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q4_K_S.gguf) | Q4_K_S | 10.53GB |
| [UnFimbulvetr-20B.Q4_K.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q4_K.gguf) | Q4_K | 11.14GB |
| [UnFimbulvetr-20B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q4_K_M.gguf) | Q4_K_M | 11.14GB |
| [UnFimbulvetr-20B.Q4_1.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q4_1.gguf) | Q4_1 | 11.61GB |
| [UnFimbulvetr-20B.Q5_0.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q5_0.gguf) | Q5_0 | 12.76GB |
| [UnFimbulvetr-20B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q5_K_S.gguf) | Q5_K_S | 12.76GB |
| [UnFimbulvetr-20B.Q5_K.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q5_K.gguf) | Q5_K | 13.11GB |
| [UnFimbulvetr-20B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q5_K_M.gguf) | Q5_K_M | 13.11GB |
| [UnFimbulvetr-20B.Q5_1.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q5_1.gguf) | Q5_1 | 13.91GB |
| [UnFimbulvetr-20B.Q6_K.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q6_K.gguf) | Q6_K | 15.2GB |
| [UnFimbulvetr-20B.Q8_0.gguf](https://huggingface.co/RichardErkhov/KaraKaraWitch_-_UnFimbulvetr-20B-gguf/blob/main/UnFimbulvetr-20B.Q8_0.gguf) | Q8_0 | 19.69GB |




Original model description:
---
base_model: ["Sao10K/Fimbulvetr-11B-v2"]
library_name: transformers
tags:
- mergekit
- merge

---
# UnFimbulvetr-20B

![](UnFimbulator.png "A Waifu that is disappointed in me with this cursed merge. ControlNet Image Source is from the original Fimbulvetr-11B-v2.")

*Waifu to catch your attention*

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

NOTE: *Only tested this just for a bit. YMMV.*

## Next Day Tests...

Downloaded the GGUF model that someone quantized... And... nope. No.

**Do not use model.**

## Merge Details
### Merge Method

This model was merged using the passthrough merge method.

### Models Merged

The following models were included in the merge:
* Sao10K/Fimbulvetr-11B-v2

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
    - model: FimbMagic
      layer_range: [0, 13]
  - sources:
    - model: FimbMagic
      layer_range: [8, 13]
  - sources:
    - model: FimbMagic
      layer_range: [12, 36]
  - sources:
    - model: FimbMagic
      layer_range: [12, 36]
  - sources:
    - model: FimbMagic
      layer_range: [36, 48]
  - sources:
    - model: FimbMagic
      layer_range: [36, 48]
merge_method: passthrough
dtype: bfloat16
```

### Additional Notes

Fimbulvetr 11B is still a very good model. This model is for extreme trailblazers who wants to test stuff!

Eval results? Don't bother.

Last one before I sleep: *I'm so sorry Sao10K...*