---
title: Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF
canonical_url: "https://www.modelscope.cn/models/LLM-Research/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF"
md_url: "https://www.modelscope.cn/models/LLM-Research/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF.md"
repository: LLM-Research/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF
last_updated: 2024-09-10
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 2162
stars: 0
tags:
  - llama-cpp
  - gguf-my-repo
  - gguf
---

# Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF

> Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF - LLM-Research 在 ModelScope 开源的模型。leafspark/Meta-Llama-3.1-8B-Instruct-hf-Q6K-GGUF This model was converted to GGUF format from alpindale/Meta-Llama-3.1-8B-Instruct-hf using llama.cpp via the ggml.ai's GGUF-my-repo…

- **Repository**: LLM-Research/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF
- **Tags**: llama-cpp, gguf-my-repo, gguf
- **Downloads**: 2162
- **Stars**: 0
- **Last updated**: 2024-09-10

Source: https://www.modelscope.cn/models/LLM-Research/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF

---

# leafspark/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF
This model was converted to GGUF format from [`alpindale/Meta-Llama-3.1-8B-Instruct-hf`](https://huggingface.co/alpindale/Meta-Llama-3.1-8B-Instruct-hf) 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/alpindale/Meta-Llama-3.1-8B-Instruct-hf) 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 leafspark/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF --hf-file meta-llama-3.1-8b-instruct-hf-q6_k.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo leafspark/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF --hf-file meta-llama-3.1-8b-instruct-hf-q6_k.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 leafspark/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF --hf-file meta-llama-3.1-8b-instruct-hf-q6_k.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo leafspark/Meta-Llama-3.1-8B-Instruct-hf-Q6_K-GGUF --hf-file meta-llama-3.1-8b-instruct-hf-q6_k.gguf -c 2048
```