---
license: apache-2.0
language:
- en
base_model:
- nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
- code
- reasoning
- research
---

# **Nemotron-Research-Reasoning-Qwen-1.5B-GGUF**

> [Nemotron-Research-Reasoning-Qwen-1.5B](https://huggingface.co/nvidia/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. 

## Model Files

| File Name | Format | Size | Precision | Use Case |
|-----------|--------|------|-----------|----------|
| `Nemotron-Research-Reasoning-Qwen-1.5B.F32.gguf` | GGUF | 7.11 GB | F32 | Highest precision, research use |
| `Nemotron-Research-Reasoning-Qwen-1.5B.BF16.gguf` | GGUF | 3.56 GB | BF16 | High precision, balanced performance |
| `Nemotron-Research-Reasoning-Qwen-1.5B.F16.gguf` | GGUF | 3.56 GB | F16 | High precision, memory efficient |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf` | GGUF | 1.89 GB | Q8_0 | Good quality, moderate compression |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf` | GGUF | 1.29 GB | Q5_K_M | Balanced quality/size (recommended) |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf` | GGUF | 1.26 GB | Q5_K_S | Good quality, smaller size |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf` | GGUF | 1.12 GB | Q4_K_M | Good balance for most users |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf` | GGUF | 1.07 GB | Q4_K_S | Decent quality, compact size |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf` | GGUF | 980 MB | Q3_K_L | Lower quality, very compact |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf` | GGUF | 924 MB | Q3_K_M | Fast inference, limited quality |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf` | GGUF | 861 MB | Q3_K_S | Fastest inference, basic quality |
| `Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf` | GGUF | 753 MB | Q2_K | Minimal size, experimental use |

### Quick Selection Guide

- **For Research/Development**: Use `F32` or `BF16` for maximum accuracy
- **For Production (Recommended)**: Use `Q5_K_M` for best quality/performance balance
- **For Resource-Constrained Environments**: Use `Q4_K_M` or `Q4_K_S`
- **For Edge Devices**: Use `Q3_K_M` or `Q2_K` for minimal footprint

## Quants Usage 

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)