🚀 mxbai-rerank-large-v2 GGUF Models

This project offers a series of mxbai-rerank-large-v2 GGUF models, which are designed for text ranking tasks. These models support multiple languages and provide different model formats to meet various hardware requirements and usage scenarios.

🚀 Quick Start

Installation

To use the mxbai-rerank models, you first need to install the mxbai-rerank library. You can install it using the following command:

pip install mxbai-rerank

Inference Example

Here is a simple example of using the mxbai-rerank-large-v2 model for inference:

from mxbai_rerank import MxbaiRerankV2

model = MxbaiRerankV2("mixedbread-ai/mxbai-rerank-large-v2")

query = "Who wrote 'To Kill a Mockingbird'?"
documents = [
    "'To Kill a Mockingbird' is a novel by Harper Lee published in 1960. It was immediately successful, winning the Pulitzer Prize, and has become a classic of modern American literature.",
    "The novel 'Moby-Dick' was written by Herman Melville and first published in 1851. It is considered a masterpiece of American literature and deals with complex themes of obsession, revenge, and the conflict between good and evil.",
    "Harper Lee, an American novelist widely known for her novel 'To Kill a Mockingbird', was born in 1926 in Monroeville, Alabama. She received the Pulitzer Prize for Fiction in 1961.",
    "Jane Austen was an English novelist known primarily for her six major novels, which interpret, critique and comment upon the British landed gentry at the end of the 18th century.",
    "The 'Harry Potter' series, which consists of seven fantasy novels written by British author J.K. Rowling, is among the most popular and critically acclaimed books of the modern era.",
    "'The Great Gatsby', a novel written by American author F. Scott Fitzgerald, was published in 1925. The story is set in the Jazz Age and follows the life of millionaire Jay Gatsby and his pursuit of Daisy Buchanan."
]

# Lets get the scores
results = model.rank(query, documents, return_documents=True, top_k=3)

print(results)

✨ Features

• State-of-the-art Performance: These models offer high performance and strong efficiency in text ranking tasks.
• Multilingual Support: They support over 100 languages, with outstanding performance in English and Chinese.
• Code Support: The models can handle code-related text ranking tasks.
• Long-context Support: They are capable of processing long texts effectively.

📦 Choosing the Right Model Format

Selecting the correct model format depends on your hardware capabilities and memory constraints.

BF16 (Brain Float 16) – Use if BF16 acceleration is available

• A 16-bit floating-point format designed for faster computation while retaining good precision.
• Provides similar dynamic range as FP32 but with lower memory usage.
• Recommended if your hardware supports BF16 acceleration (check your device’s specs).
• Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format.

📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization.

F16 (Float 16) – More widely supported than BF16

• A 16-bit floating-point high precision but with less of range of values than BF16.
• Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
• Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations.

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

• Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
• Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)

These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.

• IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.

  • Use case: Best for ultra-low-memory devices where even Q4_K is too large.
  • Trade-off: Lower accuracy compared to higher-bit quantizations.

• IQ3_S: Small block size for maximum memory efficiency.

  • Use case: Best for low-memory devices where IQ3_XS is too aggressive.

• IQ3_M: Medium block size for better accuracy than IQ3_S.

  • Use case: Suitable for low-memory devices where IQ3_S is too limiting.

• Q4_K: 4-bit quantization with block-wise optimization for better accuracy.

  • Use case: Best for low-memory devices where Q6_K is too large.

• Q4_0: Pure 4-bit quantization, optimized for ARM devices.

  • Use case: Best for ARM-based devices or low-memory environments.

Summary Table: Model Format Selection

📦 Included Files & Details

mxbai-rerank-large-v2-bf16.gguf

• Model weights preserved in BF16.
• Use this if you want to requantize the model into a different format.
• Best if your device supports BF16 acceleration.

mxbai-rerank-large-v2-f16.gguf

• Model weights stored in F16.
• Use if your device supports FP16, especially if BF16 is not available.

mxbai-rerank-large-v2-bf16-q8_0.gguf

• Output & embeddings remain in BF16.
• All other layers quantized to Q8_0.
• Use if your device supports BF16 and you want a quantized version.

mxbai-rerank-large-v2-f16-q8_0.gguf

• Output & embeddings remain in F16.
• All other layers quantized to Q8_0.

mxbai-rerank-large-v2-q4_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q4_K.
• Good for CPU inference with limited memory.

mxbai-rerank-large-v2-q4_k_s.gguf

• Smallest Q4_K variant, using less memory at the cost of accuracy.
• Best for very low-memory setups.

mxbai-rerank-large-v2-q6_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q6_K .

mxbai-rerank-large-v2-q8_0.gguf

• Fully Q8 quantized model for better accuracy.
• Requires more memory but offers higher precision.

mxbai-rerank-large-v2-iq3_xs.gguf

• IQ3_XS quantization, optimized for extreme memory efficiency.
• Best for ultra-low-memory devices.

mxbai-rerank-large-v2-iq3_m.gguf

• IQ3_M quantization, offering a medium block size for better accuracy.
• Suitable for low-memory devices.

mxbai-rerank-large-v2-q4_0.gguf

• Pure Q4_0 quantization, optimized for ARM devices.
• Best for low-memory environments.
• Prefer IQ4_NL for better accuracy.

📊 Performance

Benchmark Results

*Latency measured on A100 GPU

🔧 Training Details

The models were trained using a three-step process:

1. GRPO (Guided Reinforcement Prompt Optimization)
2. Contrastive Learning
3. Preference Learning

For more details, check our technical blog post.

Paper following soon.

📄 License

This project is licensed under the Apache-2.0 license.

🎓 Citation

If you use these models in your research, please cite the following paper:

@online{v2rerank2025mxbai,
  title={Baked-in Brilliance: Reranking Meets RL with mxbai-rerank-v2},
  author={Sean Lee and Rui Huang and Aamir Shakir and Julius Lipp},
  year={2025},
  url={https://www.mixedbread.com/blog/mxbai-rerank-v2},
}

🚀 If you find these models useful

Please click like ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 Network Monitor Assitant.

💬 Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.

What I'm Testing

I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function".

🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .

The other Available AI Assistants

🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can Login or Download the Free Network Monitor agent to get more tokens, Alternatively use the TestLLM .

🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)