README.md

---
license: cc-by-nc-4.0
language:
- en
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
---

# <span style="color: #7FFF7F;">Nemotron-Research-Reasoning-Qwen-1.5B GGUF Models</span>


## <span style="color: #7F7FFF;">Model Generation Details</span>

This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`ea1431b0`](https://github.com/ggerganov/llama.cpp/commit/ea1431b0fa3a8108aac1e0a94a13ccc4a749963e).





## **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**  

| Model Format  | Precision  | Memory Usage  | Device Requirements  | Best Use Case  |  
|--------------|------------|---------------|----------------------|---------------|  
| **BF16**     | Highest    | High          | BF16-supported GPU/CPUs  | High-speed inference with reduced memory |  
| **F16**      | High       | High          | FP16-supported devices | GPU inference when BF16 isn't available |  
| **Q4_K**     | Medium Low | Low           | CPU or Low-VRAM devices | Best for memory-constrained environments |  
| **Q6_K**     | Medium     | Moderate      | CPU with more memory | Better accuracy while still being quantized |  
| **Q8_0**     | High       | Moderate      | CPU or GPU with enough VRAM | Best accuracy among quantized models |  
| **IQ3_XS**   | Very Low   | Very Low      | Ultra-low-memory devices | Extreme memory efficiency and low accuracy |  
| **Q4_0**     | Low        | Low           | ARM or low-memory devices | llama.cpp can optimize for ARM devices |  

---

## **Included Files & Details**  

### `Nemotron-Research-Reasoning-Qwen-1.5B-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**.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-f16.gguf`  
- Model weights stored in **F16**.  
- Use if your device supports **FP16**, especially if BF16 is not available.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-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.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-f16-q8_0.gguf`  
- **Output & embeddings** remain in **F16**.  
- All other layers quantized to **Q8_0**.    

### `Nemotron-Research-Reasoning-Qwen-1.5B-q4_k.gguf`  
- **Output & embeddings** quantized to **Q8_0**.  
- All other layers quantized to **Q4_K**.  
- Good for **CPU inference** with limited memory.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-q4_k_s.gguf`  
- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
- Best for **very low-memory setups**.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-q6_k.gguf`  
- **Output & embeddings** quantized to **Q8_0**.  
- All other layers quantized to **Q6_K** .  

### `Nemotron-Research-Reasoning-Qwen-1.5B-q8_0.gguf`  
- Fully **Q8** quantized model for better accuracy.  
- Requires **more memory** but offers higher precision.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-iq3_xs.gguf`  
- **IQ3_XS** quantization, optimized for **extreme memory efficiency**.  
- Best for **ultra-low-memory devices**.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-iq3_m.gguf`  
- **IQ3_M** quantization, offering a **medium block size** for better accuracy.  
- Suitable for **low-memory devices**.  

### `Nemotron-Research-Reasoning-Qwen-1.5B-q4_0.gguf`  
- Pure **Q4_0** quantization, optimized for **ARM devices**.  
- Best for **low-memory environments**.
- Prefer IQ4_NL for better accuracy.

# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
❤ **Please click "Like" if you find this useful!**  
Help me test my **AI-Powered Network Monitor Assistant** with **quantum-ready security checks**:  
👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  

💬 **How to test**:  
 Choose an **AI assistant type**:  
   - `TurboLLM` (GPT-4o-mini)  
   - `HugLLM` (Hugginface Open-source)  
   - `TestLLM` (Experimental CPU-only)  

### **What I’m Testing**  
I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
- **Function calling** against live network services  
- **How small can a model go** while still handling:  
  - Automated **Nmap scans**  
  - **Quantum-readiness checks**  
  - **Network Monitoring tasks**  

🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads):  
- ✅ **Zero-configuration setup**  
- ⏳ 30s load time (slow inference but **no API costs**)  
- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  

### **Other Assistants**  
🟢 **TurboLLM** – Uses **gpt-4o-mini** for: 
- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
- **Real-time network diagnostics and monitoring**
- **Security Audits**
- **Penetration testing** (Nmap/Metasploit)  
  

🔵 **HugLLM** – Latest Open-source models:  
- 🌐 Runs on Hugging Face Inference API  

### 💡 **Example commands to you could test**:  
1. `"Give me info on my websites SSL certificate"`  
2. `"Check if my server is using quantum safe encyption for communication"`  
3. `"Run a comprehensive security audit on my server"`
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!

### Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.

If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊




<div align="center">
<span style="font-family: default; font-size: 1.5em;">Nemotron-Research-Reasoning-Qwen-1.5B</span>
<div>
🚀 The leading generalist reasoning model for cutting-edge research and development 🌟
</div>
</div>

![Comparison between DeepSeek-R1-1.5B and Nemotron-Research-Reasoning-Qwen-1.5B](./assets/deepseek_vs_nvidia102.png)

## Introduction
Nemotron-Research-Reasoning-Qwen-1.5B is the world’s leading 1.5B open-weight model for complex reasoning tasks such as mathematical problems, coding challenges, scientific questions, and logic puzzles.
It is trained using the ProRL algorithm on a diverse and comprehensive set of datasets.
Our model has achieved impressive results, outperforming Deepseek’s 1.5B model by a large margin on a broad range of tasks, including math, coding, and GPQA.

This model is for research and development only.

## ProRL: Prolonged Reinforcement Learning
ProRL is designed to enable extended RL training periods that facilitate deeper exploration of reasoning strategies. 
It enables more than 2k training steps and scale the training data across diverse tasks—from traditional math and code tasks to STEM problems, logical puzzles, and instruction following, which, we hypothesize, are crucial for generalization. 
Based on Group Relative Policy Optimization (GRPO), ProRL introduces three key techniques:
1. Mitigating Entropy Collapse
2. Decoupled clip and dynamic sampling policy optimization (DAPO)
3. KL regularization and reference policy reset 

Using ProRL, we developed the world's best 1.5B reasoning model that significantly outperforms its base model, DeepSeek-R1-1.5B, and matches or even surpasses the performance of DeepSeek-R1-7B across a diverse range of benchmarks. 
Notably, compared to DeepSeek-R1-1.5B, we achieve average pass@1 improvements of 14.7\% on math benchmarks, 13.9\% on coding, 54.8\% on logic puzzles, 25.1\% on STEM reasoning, and 18.1\% on instruction-following tasks. 

## Training Datasets
| Dataset                      | Link                                                                                         |
|---------------------------|-------------------------------------------------------------------------------------------|
| DeepScaleR-Preview-Dataset  | [Link](https://huggingface.co/datasets/agentica-org/DeepScaleR-Preview-Dataset)                   |
| Eurus-2-RL-Data           | [Link](https://huggingface.co/datasets/PRIME-RL/Eurus-2-RL-Data)                             |
| Reasoning-gym            | [Link](https://github.com/open-thought/reasoning-gym)                                        |
| IFEval                     | [Link](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset)   |
| SCP-116K                   | [Link](https://huggingface.co/datasets/EricLu/SCP-116K)                                  |


## Evaluation Results

Table 1: Performance (pass@1) comparison for benchmarks across Math domain. 
| Model                          | AIME24 | AIME25 | AMC   | Math  | Minerva | Olympiad | Avg   |
|-------------------------------|--------|--------|-------|-------|----------|----------|--------|
| DeepSeek-R1-Distill-Qwen-1.5B | 28.54  | 22.71  | 62.58 | 82.90 | 26.38    | 43.58    | 44.45  |
| DeepScaleR-1.5B               | 40.21  | 31.46  | 73.04 | 89.36 | 41.57    | 51.63    | 54.54  |
| *DeepSeek-R1-Distill-Qwen-7B* | 53.54  | 40.83  | 82.83 | 93.68 | 50.60    | 57.66    | 63.19  |
| **Nemotron-Research-Reasoning-Qwen-1.5B**                 | **48.13** | **33.33** | **79.29** | **91.89** | **47.98** | **60.22** | **60.14** |

Table 2: Performance (pass@1) comparison across benchmarks for Code. We abbreviate benchmarks names for condecontests (cc), codeforces (cf), humanevalplus (human), and livecodebench (LCB).
| Model                          | apps  | cc    | cf    | taco  | human | LCB   | Avg    |
|-------------------------------|--------|--------|--------|--------|--------|--------|--------|
| DeepSeek-R1-Distill-Qwen-1.5B | 20.95  | 16.79 | 14.13 | 8.03  | 61.77 | 16.80 | 23.08  |
| DeepCoder-1.5B                | 30.37  | 23.76 | 21.70 | 13.76 | 73.40 | 22.76 | 30.96  |
| *DeepSeek-R1-Distill-Qwen-7B* | 42.08  | 32.76 | 33.08 | 19.08 | 83.32 | 38.04 | 41.39  |
| **Nemotron-Research-Reasoning-Qwen-1.5B**                 | **41.99** | **31.80** | **34.50** | **20.81** | 72.05 | **23.81** | **37.49** |

Table 3: Performance comparison on STEM reasoning (GPQA Diamond), instruction following (IFEval), and logic puzzles (Reasoning Gym) tasks. We also present results on OOD tasks: acre, boxnet, and game_of_life_halting (game).
| Model                          | GPQA  | IFEval | Reasoning | acre  | boxnet | game  |
|-------------------------------|--------|--------|-----------|--------|--------|--------|
| DeepSeek-R1-Distill-Qwen-1.5B | 15.86  | 44.05  | 4.24      | 5.99  | 0.00   | 3.49  |
| *DeepSeek-R1-Distill-Qwen-7B* | 35.44  | 58.01  | 28.55     | 20.21 | 1.71   | 12.94 |
| **Nemotron-Research-Reasoning-Qwen-1.5B**                 | **41.78** | **66.02** | **59.06** | **58.57** | **7.91** | **52.29** |


## License/Terms of Use
cc-by-nc-4.0

## Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

## Citation
If you find our dataset helpful, please cite the following [paper](https://arxiv.org/abs/2505.24864):

```
@article{liu2025prorl,
  author    = {Mingjie Liu, Shizhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, Yi Dong},
  title={ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models}, 
  journal   = {arXiv preprint},
  year      = {2025},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url={https://arxiv.org/abs/2505.24864}, 
}
```