Instructions to use cstr/mxbai-rerank-base-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/mxbai-rerank-base-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cstr/mxbai-rerank-base-v1-GGUF",
	filename="mxbai-rerank-base-v1-q4_k.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cstr/mxbai-rerank-base-v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cstr/mxbai-rerank-base-v1-GGUF:Q8_0

Use Docker

docker model run hf.co/cstr/mxbai-rerank-base-v1-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use cstr/mxbai-rerank-base-v1-GGUF with Ollama:
```
ollama run hf.co/cstr/mxbai-rerank-base-v1-GGUF:Q8_0
```

Unsloth Studio

How to use cstr/mxbai-rerank-base-v1-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cstr/mxbai-rerank-base-v1-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cstr/mxbai-rerank-base-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cstr/mxbai-rerank-base-v1-GGUF to start chatting

Docker Model Runner
How to use cstr/mxbai-rerank-base-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/cstr/mxbai-rerank-base-v1-GGUF:Q8_0
```

Lemonade

How to use cstr/mxbai-rerank-base-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cstr/mxbai-rerank-base-v1-GGUF:Q8_0

Run and chat with the model

lemonade run user.mxbai-rerank-base-v1-GGUF-Q8_0

List all available models

lemonade list

cstr commited on Apr 17

Commit

3eabb58

verified ·

1 Parent(s): 3728af7

Add model card for mxbai-rerank-base-v1 GGUF

Browse files

Files changed (1) hide show

README.md +77 -0

README.md ADDED Viewed

	@@ -0,0 +1,77 @@

+---
+license: apache-2.0
+language: [en]
+tags: [embeddings, gguf, ggml, text-embeddings, bert, crispembed]
+pipeline_tag: feature-extraction
+base_model: mixedbread-ai/mxbai-rerank-base-v1
+---
+# mxbai-rerank-base-v1 GGUF
+GGUF format of [mixedbread-ai/mxbai-rerank-base-v1](https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v1) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed).
+MixedBread Rerank Base v1. Cross-encoder reranker for English, good quality/speed balance.
+## Files
+| File | Quantization | Size |
+|------|-------------|------|
+| [mxbai-rerank-base-v1-q4_k.gguf](https://huggingface.co/cstr/mxbai-rerank-base-v1-GGUF/resolve/main/mxbai-rerank-base-v1-q4_k.gguf) | Q4_K | 149 MB |
+| [mxbai-rerank-base-v1-q8_0.gguf](https://huggingface.co/cstr/mxbai-rerank-base-v1-GGUF/resolve/main/mxbai-rerank-base-v1-q8_0.gguf) | Q8_0 | 190 MB |
+| [mxbai-rerank-base-v1.gguf](https://huggingface.co/cstr/mxbai-rerank-base-v1-GGUF/resolve/main/mxbai-rerank-base-v1.gguf) | F32 | 706 MB |
+## Quick Start
+```bash
+# Download
+huggingface-cli download cstr/mxbai-rerank-base-v1-GGUF mxbai-rerank-base-v1-q4_k.gguf --local-dir .
+# Run with CrispEmbed
+./crispembed -m mxbai-rerank-base-v1-q4_k.gguf "Hello world"
+# Or with auto-download
+./crispembed -m mxbai-rerank-base-v1 "Hello world"
+```
+## Model Details
+| Property | Value |
+|----------|-------|
+| Architecture | BERT |
+| Parameters | 86M |
+| Embedding Dimension | 768 |
+| Layers | 12 |
+| Pooling | CLS |
+| Tokenizer | WordPiece |
+| Base Model | [mixedbread-ai/mxbai-rerank-base-v1](https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v1) |
+## Verification
+Verified bit-identical to HuggingFace sentence-transformers (cosine similarity >= 0.999 on test texts).
+## Usage with CrispEmbed
+CrispEmbed is a lightweight C/C++ text embedding inference engine using ggml.
+No Python runtime, no ONNX. Supports BERT, XLM-R, Qwen3, and Gemma3 architectures.
+```bash
+# Build CrispEmbed
+git clone https://github.com/CrispStrobe/CrispEmbed
+cd CrispEmbed
+cmake -S . -B build && cmake --build build -j
+# Encode
+./build/crispembed -m mxbai-rerank-base-v1-q4_k.gguf "query text"
+# Server mode
+./build/crispembed-server -m mxbai-rerank-base-v1-q4_k.gguf --port 8080
+curl -X POST http://localhost:8080/v1/embeddings \
+    -d '{"input": ["Hello world"], "model": "mxbai-rerank-base-v1"}'
+```
+## Credits
+- Original model: [mixedbread-ai/mxbai-rerank-base-v1](https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v1)
+- Inference engine: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (ggml-based)
+- Conversion: `convert-bert-embed-to-gguf.py`