---
language:
- en
library_name: transformers
pipeline_tag: text-generation
quantized_by: mradermacher
tags:
- llama
- llama 2
---
## About

static quantize of https://huggingface.co/Doctor-Shotgun/lzlv-limarpv3-l2-70b
<!-- 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 |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q2_K.gguf) | Q2_K | 25.5 |  |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q3_K_XS.gguf) | Q3_K_XS | 28.3 |  |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q3_K_S.gguf) | Q3_K_S | 29.9 |  |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q3_K_M.gguf) | Q3_K_M | 33.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q3_K_L.gguf) | Q3_K_L | 36.1 |  |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q4_K_S.gguf) | Q4_K_S | 39.2 | fast, medium quality |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q4_K_M.gguf) | Q4_K_M | 41.4 | fast, medium quality |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q5_K_S.gguf) | Q5_K_S | 47.5 |  |
| [GGUF](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q5_K_M.gguf) | Q5_K_M | 48.8 |  |
| [PART 1](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q6_K.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q6_K.gguf.split-ab) | Q6_K | 56.6 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q8_0.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/lzlv-limarpv3-l2-70b-GGUF/resolve/main/lzlv-limarpv3-l2-70b.Q8_0.gguf.split-ab) | Q8_0 | 73.3 | fast, best quality |


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

![image.png](https://cdn-uploads.huggingface.co/production/uploads/645ce413a19f3e64bbeece31/dEiT6xDvxyANdetzVG1tX.png)

<!-- end -->