NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 — GGUF Quantizations
Quantized GGUF versions of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Works with llama.cpp · Ollama · LM Studio · Open WebUI · Jan
Quantized by Dhptl on June 17, 2026 using quant-kit
⚖️ 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.
| Benchmark | Original (FP16) | Q4_K_M | Quality Retained |
|---|---|---|---|
| MMLU Pro | See original card | Run benchmarks | ~97-99% |
| HellaSwag | See original card | Run benchmarks | ~97-99% |
| ARC Challenge | See original card | Run benchmarks | ~97-99% |
| TruthfulQA | See original card | Run benchmarks | ~97-99% |
| GSM8K | See original card | Run benchmarks | ~97-99% |
📦 Available Files
| Filename | Size | RAM Required | Quant | Quality | Best For |
|---|
💡 Which file should I download?
- Most users:
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-Q4_K_M.gguf— best balance of size and quality - High RAM (32GB+):
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-Q8_0.gguf— near-original quality - Low RAM (8GB):
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-Q3_K_M.gguf— fits in 8GB with room to spare
⚡ Speed Benchmarks
Run python benchmark.py --model NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 to generate speed results.
🧠 Quality Benchmarks
Run kaggle_bench.ipynb on Kaggle to benchmark this model.
🚀 How to Use
Ollama
ollama run dhptl/nvidia-nemotron-3-nano-30b-a3b-bf16
LM Studio / Jan / Open WebUI
Search for Dhptl/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 in the model browser.
llama.cpp CLI
# Download the binary from https://github.com/ggerganov/llama.cpp/releases
./llama-cli \
-m NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-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="./NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-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:
| Format | Bits/weight | Size vs FP16 | Quality |
|---|---|---|---|
| Q2_K | ~2.6 | 16% | ⭐ |
| Q3_K_M | ~3.3 | 21% | ⭐⭐⭐ |
| Q4_K_M | ~4.5 | 28% | ⭐⭐⭐⭐ ← sweet spot |
| Q5_K_M | ~5.6 | 35% | ⭐⭐⭐⭐½ |
| Q8_0 | ~8.5 | 53% | ⭐⭐⭐⭐⭐ |
💬 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