DhruvalLabs/Nanbeige4.1-3B-GGUF

<div align="center">

Nanbeige4.1-3B — GGUF Quantizations

  

Quantized GGUF versions of [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B)

Works with [llama.cpp](https://github.com/ggerganov/llama.cpp) · [Ollama](https://ollama.ai) · [LM Studio](https://lmstudio.ai) · [Open WebUI](https://openwebui.com) · [Jan](https://jan.ai)

Quantized by [Dhptl](https://huggingface.co/Dhptl) on June 18, 2026 using [quant-kit](https://github.com/DhruvalPtl/quant-kit)

</div>

⚖️ The Pareto Frontier — Efficiency vs Intelligence

Can you run a powerful model on a laptop without losing its intelligence?

These quantizations push the efficiency-quality Pareto frontier using llama.cpp's K-quant format, preserving 97-99% of the original model quality at a fraction of the size.

📦 Available Files

💡 Which file should I download?

• —Most users: Nanbeige4.1-3B-Q4_K_M.gguf — best balance of size and quality
• —High RAM (32GB+): Nanbeige4.1-3B-Q8_0.gguf — near-original quality
• —Low RAM (8GB): Nanbeige4.1-3B-Q3_K_M.gguf — fits in 8GB with room to spare

⚡ Speed Benchmarks

Run `python benchmark.py --model Nanbeige4.1-3B` to generate speed results.

🧠 Quality Benchmarks

Run `kaggle_bench.ipynb` on Kaggle to benchmark this model.

🚀 How to Use

Ollama

ollama run dhptl/nanbeige4.1-3b

LM Studio / Jan / Open WebUI

Search for Dhptl/Nanbeige4.1-3B in the model browser.

llama.cpp CLI

# Download the binary from https://github.com/ggerganov/llama.cpp/releases
./llama-cli \
  -m Nanbeige4.1-3B-Q4_K_M.gguf \
  -p "You are a helpful assistant." \
  --conversation \
  -n 512

Python — llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="./Nanbeige4.1-3B-Q4_K_M.gguf",
    n_gpu_layers=-1,   # -1 = offload everything to GPU
    n_ctx=4096,
)

response = llm.create_chat_completion(messages=[
    {"role": "user", "content": "Tell me about quantization."}
])
print(response["choices"][0]["message"]["content"])

🔍 About GGUF Quantization

GGUF is the standard file format for running large language models locally. Quantization reduces the number of bits per weight:

💬 Community & Feedback

Found an issue? Have a question? Open a Discussion in the Community tab above.

If these quantizations were useful, please consider:

• —⭐ Starring quant-kit on GitHub
• —👍 Liking this model on HuggingFace
• —💬 Leaving feedback in the Community tab