---
title: Yi-1.5-9B-32K-GGUF
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Yi-1.5-9B-32K-GGUF"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Yi-1.5-9B-32K-GGUF.md"
repository: AI-ModelScope/Yi-1.5-9B-32K-GGUF
last_updated: 2024-08-12
license: apache-2.0
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2042
stars: 1
tags:
  - gguf
---

# Yi-1.5-9B-32K-GGUF

> Yi-1.5-9B-32K-GGUF - AI-ModelScope 在 ModelScope 开源的模型。static quants of https://huggingface.co/01-ai/Yi-1.5-9B-32K

AI-ModelScope/Yi-1.5-9B-32K-GGUF 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/Yi-1.5-9B-32K-GGUF
- **License**: apache-2.0
- **Tags**: gguf
- **Downloads**: 2042
- **Stars**: 1
- **Last updated**: 2024-08-12

Source: https://www.modelscope.cn/models/AI-ModelScope/Yi-1.5-9B-32K-GGUF

---

## About

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type:  -->
<!-- ### tags:  -->
static quants of https://huggingface.co/01-ai/Yi-1.5-9B-32K

<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-1.5-9B-32K-i1-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/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q2_K.gguf) | Q2_K | 3.5 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.IQ3_XS.gguf) | IQ3_XS | 3.8 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q3_K_S.gguf) | Q3_K_S | 4.0 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.IQ3_M.gguf) | IQ3_M | 4.2 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q3_K_L.gguf) | Q3_K_L | 4.8 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.IQ4_XS.gguf) | IQ4_XS | 4.9 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q5_K_S.gguf) | Q5_K_S | 6.2 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q5_K_M.gguf) | Q5_K_M | 6.4 |  |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q6_K.gguf) | Q6_K | 7.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.Q8_0.gguf) | Q8_0 | 9.5 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-32K-GGUF/resolve/main/Yi-1.5-9B-32K.f16.gguf) | f16 | 17.8 | 16 bpw, overkill |

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 -->