---
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
---
## About

static quants of https://huggingface.co/NobodyExistsOnTheInternet/Llama-2-70b-x8-MoE-clown-truck

How did so many fit into that?

<!-- provided-files -->
## 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/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q2_K.gguf.part4of4) | Q2_K | 170.8 |  |
| [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_S.gguf.part1of5) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_S.gguf.part2of5) [PART 3](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_S.gguf.part3of5) [PART 4](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_S.gguf.part4of5) [PART 5](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_S.gguf.part5of5) | Q3_K_S | 202.0 |  |
| [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_M.gguf.part1of5) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_M.gguf.part2of5) [PART 3](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_M.gguf.part3of5) [PART 4](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_M.gguf.part4of5) [PART 5](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q3_K_M.gguf.part5of5) | Q3_K_M | 223.1 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q4_K_M.gguf.part1of6) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q4_K_M.gguf.part2of6) [PART 3](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q4_K_M.gguf.part3of6) [PART 4](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q4_K_M.gguf.part4of6) [PART 5](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q4_K_M.gguf.part5of6) [PART 6](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q4_K_M.gguf.part6of6) | Q4_K_M | 282.0 | fast, medium quality |
| [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part1of8) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part2of8) [PART 3](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part3of8) [PART 4](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part4of8) [PART 5](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part5of8) [PART 6](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part6of8) [PART 7](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part7of8) [PART 8](https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-GGUF/resolve/main/Llama-2-70b-x8-MoE-clown-truck.Q6_K.gguf.part8of8) | Q6_K | 381.0 | very good 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

<!-- end -->