---
title: gpt-oss-nano
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/gpt-oss-nano"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/gpt-oss-nano.md"
repository: AI-ModelScope/gpt-oss-nano
last_updated: 2026-07-14
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gpt_oss
architectures:
  - GptOssForCausalLM
base_model:
  - openai/gpt-oss-20b
base_model_relation: quantized
parameters: 9.0B
tensor_type:
  - BF16
  - F32
library_name:
  - pytorch
  - transformer
  - gguf
  - safetensors
frameworks:
  - pytorch
language:
  - en
downloads: 191
stars: 1
tags:
  - gpt-oss
  - reasoning
  - moe
  - mixture-of-experts
  - chain-of-thought
  - unsloth
  - gguf
  - llama-cpp
---

# gpt-oss-nano

> gpt-oss-nano - AI-ModelScope 在 ModelScope 开源的模型。Compact Reasoning Model with Mixture of Experts

AI-ModelScope/gpt-oss-nano 是 ModelScope 魔搭社区上的 9.0B 参数text-generation模型，采用 apache-2.0 许可，基于 openai/gpt-oss-20b 构建。

- **Repository**: AI-ModelScope/gpt-oss-nano
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 9.0B
- **Base model**: openai/gpt-oss-20b
- **Tags**: gpt-oss, reasoning, moe, mixture-of-experts, chain-of-thought, unsloth, gguf, llama-cpp
- **Downloads**: 191
- **Stars**: 1
- **Last updated**: 2026-07-14

Source: https://www.modelscope.cn/models/AI-ModelScope/gpt-oss-nano

---

<div align="center">

# GPT-OSS-Nano

![nan1](https://cdn-uploads.huggingface.co/production/uploads/67329d3f69fded92d56ab41a/mUoPeO4k7zXj50NpH6FdN.jpeg)

### Compact Reasoning Model with Mixture of Experts

[![Unsloth](https://img.shields.io/badge/🦥_Unsloth-2x_Faster_Training-5865F2?style=for-the-badge)](https://github.com/unslothai/unsloth)
[![GGUF](https://img.shields.io/badge/📦_GGUF-Available-00D9FF?style=for-the-badge)](#gguf-files)
[![License](https://img.shields.io/badge/📜_License-Apache_2.0-green?style=for-the-badge)](https://www.apache.org/licenses/LICENSE-2.0)
[![Socket Badge](https://badge.socket.dev/huggingface/package/squ11z1/gpt-oss-nano?version=69620c60bd3e828ceb666af71239a6d84386a6fa)](https://badge.socket.dev/huggingface/package/squ11z1/gpt-oss-nano?version=69620c60bd3e828ceb666af71239a6d84386a6fa)

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="180"/>

**9B parameters • 12 experts • 128K context • Chain-of-thought reasoning**

[🤗 Model](https://huggingface.co/squ11z1/gpt-oss-9b-reasoning) | [📖 Docs](#usage) | [🔮 Q-GPT](https://huggingface.co/squ11z1/Q-GPT)

</div>

---

## 📋 Model Description

**GPT-OSS-Nano** is a fine-tuned Mixture of Experts (MoE) language model optimized for **step-by-step reasoning** and problem solving. Built on the GPT-OSS architecture with sparse expert activation, it achieves strong reasoning performance while using only ~3B active parameters per forward pass.

### ✨ Key Features

| Feature | Description |
|---------|-------------|
| 🧠 **Sparse MoE** | 12 experts, 4 active per token — efficient compute |
| 📝 **Chain-of-Thought** | Fine-tuned on reasoning datasets with step-by-step solutions |
| ⚡ **128K Context** | Long context with YaRN rope scaling |
| 🔮 **Q-GPT Ready** | Compatible with quantum confidence estimation |
| 📦 **GGUF Available** | Run locally with llama.cpp or Ollama |

---

## 🏗️ Architecture

```
┌─────────────────────────────────────────────────────────┐
│                    GPT-OSS-Nano                         │
├─────────────────────────────────────────────────────────┤
│  Total Parameters     │  9.0 Billion                    │
│  Active Parameters    │  ~3 Billion (per forward pass)  │
│  Hidden Dimension     │  2880                           │
│  Attention Heads      │  64 (8 KV heads, GQA)           │
│  Layers               │  24                             │
│  Experts              │  12 total, 4 active             │
│  Context Length       │  131,072 tokens                 │
│  Vocabulary Size      │  201,088                        │
│  Precision            │  BFloat16                       │
└─────────────────────────────────────────────────────────┘
```

---

## 💻 Usage

### Quick Start with Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "squ11z1/gpt-oss-nano",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "squ11z1/gpt-oss-nano",
    trust_remote_code=True,
)

prompt = """Solve this step by step:
A store offers 20% off on all items. If a jacket costs $85, 
what is the final price after discount?"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    temperature=0.7,
    do_sample=True,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### ⚡ With Unsloth (2x Faster)

```python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "squ11z1/gpt-oss-nano",
    dtype=None,
    load_in_4bit=True,  # 4-bit quantization for efficiency
)

# For inference
FastLanguageModel.for_inference(model)
```

### 📦 With GGUF (llama.cpp)

```bash
# Download the quantized model
wget https://huggingface.co/squ11z1/gpt-oss-nano/resolve/main/gpt-oss-9b-q4_k_m.gguf

# Run inference
./llama-cli -m gpt-oss-9b-q4_k_m.gguf \
    -p "Solve step by step: What is 15% of 240?" \
    -n 256 --temp 0.7
```

### 🦙 With Ollama

```bash
# Create Modelfile
echo 'FROM ./gpt-oss-9b-q4_k_m.gguf' > Modelfile
ollama create gpt-oss-nano -f Modelfile

# Run
ollama run gpt-oss-nano "Explain quantum computing simply"
```

---

## 🎓 Training

<details>
<summary><b>Training Details</b></summary>

| Parameter | Value |
|-----------|-------|
| **Base Model** | `openai/gpt-oss-20b` |
| **Method** | QLoRA (4-bit quantized LoRA) |
| **LoRA Rank** | 32 |
| **LoRA Alpha** | 32 |
| **Learning Rate** | 2e-4 |
| **Batch Size** | 2 (gradient accumulation: 8) |
| **Epochs** | 2 |
| **Framework** | Unsloth + TRL |
| **Hardware** | NVIDIA H200 |

**Dataset:** Superior-Reasoning — chain-of-thought examples with step-by-step problem solving.

</details>

---

## 🔮 Q-GPT: Quantum Confidence

GPT-OSS-Nano is compatible with **Q-GPT** — a quantum neural network that estimates response confidence.

```python
from q_gpt import load_qgpt

model, tokenizer = load_qgpt("squ11z1/gpt-oss-nano")
outputs = model.generate_with_confidence(inputs, max_new_tokens=256)

print(f"Response confidence: {outputs['confidence_label']}")
# Output: "high", "moderate", "low", etc.

if outputs['should_refuse']:
    print("⚠️ Model is uncertain — consider refusing to answer")
```

Learn more: [squ11z1/Q-GPT](https://huggingface.co/squ11z1/Q-GPT)

---

## ⚠️ Limitations

- **Language:** Primarily optimized for English; multilingual performance varies
- **Hallucinations:** May generate plausible but incorrect information on obscure topics
- **Safety:** Not designed for safety-critical applications without validation
- **Math:** Strong at arithmetic reasoning; weaker on advanced mathematics

---

## 📜 License

This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).

---

## 🙏 Acknowledgments

- **[Unsloth](https://github.com/unslothai/unsloth)** — 2x faster fine-tuning
- **[OpenAI](https://huggingface.co/openai)** — GPT-OSS base model
- **[llama.cpp](https://github.com/ggerganov/llama.cpp)** — GGUF format and quantization

---

## 📖 Citation

```bibtex
@misc{gptossnano2026,
  title={GPT-OSS-Nano: Compact MoE Reasoning Model},
  author={squ11z1},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/squ11z1/gpt-oss-nano}
}
```

---

<div align="center">

**Pro Mundi Vita**

</div>