---
title: bge-reranker-v2-m3-Q4_K_M-GGUF
canonical_url: "https://www.modelscope.cn/models/gaoshengwinner/bge-reranker-v2-m3-Q4_K_M-GGUF"
md_url: "https://www.modelscope.cn/models/gaoshengwinner/bge-reranker-v2-m3-Q4_K_M-GGUF.md"
repository: gaoshengwinner/bge-reranker-v2-m3-Q4_K_M-GGUF
chinese_name: bge-reranker-v2-m3-Q4_K_M-GGUF
last_updated: 2026-01-20
license: apache-2.0
pipeline_tag: text-classification
tasks:
  - text-classification
base_model:
  - BAAI/bge-reranker-v2-m3
base_model_relation: finetune
library_name:
  - sentence-transformers
  - tensorflow
frameworks:
  - Tensorflow
language:
  - multilingual
downloads: 720
stars: 1
tags:
  - transformers
  - sentence-transformers
  - text-embeddings-inference
  - llama-cpp
  - gguf-my-repo
  - gguf
---

# bge-reranker-v2-m3-Q4_K_M-GGUF

> bge-reranker-v2-m3-Q4_K_M-GGUF - gaoshengwinner 在 ModelScope 开源的模型。puppyM/bge-reranker-v2-m3-Q4KM-GGUF This model was converted to GGUF format from BAAI/bge-reranker-v2-m3 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card…

gaoshengwinner/bge-reranker-v2-m3-Q4_K_M-GGUF 是 ModelScope 魔搭社区上的text-classification模型，采用 apache-2.0 许可，基于 BAAI/bge-reranker-v2-m3 构建。

- **Repository**: gaoshengwinner/bge-reranker-v2-m3-Q4_K_M-GGUF
- **License**: apache-2.0
- **Tasks**: text-classification
- **Base model**: BAAI/bge-reranker-v2-m3
- **Tags**: transformers, sentence-transformers, text-embeddings-inference, llama-cpp, gguf-my-repo, gguf
- **Downloads**: 720
- **Stars**: 1
- **Last updated**: 2026-01-20

Source: https://www.modelscope.cn/models/gaoshengwinner/bge-reranker-v2-m3-Q4_K_M-GGUF

---

# puppyM/bge-reranker-v2-m3-Q4_K_M-GGUF
This model was converted to GGUF format from [`BAAI/bge-reranker-v2-m3`](https://huggingface.co/BAAI/bge-reranker-v2-m3) 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/BAAI/bge-reranker-v2-m3) 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 puppyM/bge-reranker-v2-m3-Q4_K_M-GGUF --hf-file bge-reranker-v2-m3-q4_k_m.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo puppyM/bge-reranker-v2-m3-Q4_K_M-GGUF --hf-file bge-reranker-v2-m3-q4_k_m.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 puppyM/bge-reranker-v2-m3-Q4_K_M-GGUF --hf-file bge-reranker-v2-m3-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo puppyM/bge-reranker-v2-m3-Q4_K_M-GGUF --hf-file bge-reranker-v2-m3-q4_k_m.gguf -c 2048
```
