---
title: KURE-v1-Q8_0-GGUF
canonical_url: "https://www.modelscope.ai/models/Bing-su/KURE-v1-Q8_0-GGUF"
md_url: "https://www.modelscope.ai/models/Bing-su/KURE-v1-Q8_0-GGUF.md"
repository: Bing-su/KURE-v1-Q8_0-GGUF
last_updated: 2026-01-05
license: mit
pipeline_tag: feature-extraction
tasks:
  - feature-extraction
base_model:
  - nlpai-lab/KURE-v1
base_model_relation: quantized
library_name:
  - sentence-transformers
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - ko
  - en
downloads: 128
stars: 0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - "dataset_size:1879136"
  - "loss:CachedGISTEmbedLoss"
  - llama-cpp
  - gguf-my-repo
  - gguf
---

# KURE-v1-Q8_0-GGUF

> KURE-v1-Q8_0-GGUF - An open-source model by Bing-su on ModelScope. Bingsu/KURE-v1-Q80-GGUF This model was converted to GGUF format from mykor/KURE-v1 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on…

Bing-su/KURE-v1-Q8_0-GGUF is a feature-extraction model on ModelScope. licensed under mit. derived from nlpai-lab/KURE-v1.

- **Repository**: Bing-su/KURE-v1-Q8_0-GGUF
- **License**: mit
- **Tasks**: feature-extraction
- **Base model**: nlpai-lab/KURE-v1
- **Tags**: sentence-transformers, sentence-similarity, feature-extraction, generated_from_trainer, dataset_size:1879136, loss:CachedGISTEmbedLoss, llama-cpp, gguf-my-repo, gguf
- **Downloads**: 128
- **Stars**: 0
- **Last updated**: 2026-01-05

Source: https://www.modelscope.ai/models/Bing-su/KURE-v1-Q8_0-GGUF

---

# Bingsu/KURE-v1-Q8_0-GGUF
This model was converted to GGUF format from [`mykor/KURE-v1`](https://huggingface.co/mykor/KURE-v1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/mykor/KURE-v1) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo Bingsu/KURE-v1-Q8_0-GGUF --hf-file kure-v1-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Bingsu/KURE-v1-Q8_0-GGUF --hf-file kure-v1-q8_0.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Bingsu/KURE-v1-Q8_0-GGUF --hf-file kure-v1-q8_0.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Bingsu/KURE-v1-Q8_0-GGUF --hf-file kure-v1-q8_0.gguf -c 2048
```