---
language:
  - en
  - fa
license: apache-2.0
tags:
  - medical
  - biology
  - persian
  - farsi
  - llama-3
  - chain-of-thought
  - healthcare
  - clinical-reasoning
  - bilingual
  - gguf
  - quantized
  - ollama
  - llama-cpp
  - lm-studio
base_model: HexQuant/Pars-Medical-o1-Llama-FFT
pipeline_tag: text-generation
---

<div align="center">

# 🩺 Pars-Medical-o1-Llama-FFT-GGUF - ⚠️This is a beta version and does not have the ability to correctly respond to or handle local runs on its own.⚠️
## ⚠️The full version will be released in the Pars-Medical application.⚠️

### نسخه کوانتیزه شده برای اجرای محلی
### Quantized Version for Local Inference



![image](https://cdn-uploads.huggingface.co/production/uploads/66c1fd184511077b9f3cd432/PUFgx3Ya51uylZkgjf0EI.png)

[![Main Model](https://img.shields.io/badge/🤗_Main_Model-BF16-blue?style=for-the-badge)](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT)
[![GGUF](https://img.shields.io/badge/📦_This_Repo-GGUF-green?style=for-the-badge)](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT-GGUF)
[![License](https://img.shields.io/badge/📜_License-Apache_2.0-orange?style=for-the-badge)](LICENSE)

[![Twitter](https://img.shields.io/badge/Twitter-@TheRealPourya-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/TheRealPourya)
[![GitHub](https://img.shields.io/badge/GitHub-xPOURY4-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/xPOURY4)
[![HuggingFace](https://img.shields.io/badge/🤗_HuggingFace-HexQuant-FFD21E?style=for-the-badge)](https://huggingface.co/HexQuant)

</div>

---

## 📦 About This Repo | درباره این ریپو

<table>
<tr>
<td width="50%" align="right" dir="rtl">

این ریپو شامل نسخه‌های **کوانتیزه شده GGUF** از مدل [Pars-Medical-o1-Llama-FFT](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT) است.

برای اجرای **محلی** با Ollama، LM Studio یا llama.cpp مناسب است.

</td>
<td width="50%">

This repo contains **GGUF quantized versions** of [Pars-Medical-o1-Llama-FFT](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT).

Perfect for **local inference** with Ollama, LM Studio, or llama.cpp.

</td>
</tr>
</table>

> 🔗 **Looking for full model?** See [Pars-Medical-o1-Llama-FFT](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT) (BF16, 6.4GB)

---

## 📊 Available Quantizations | نسخه‌های موجود

> Quantized on **NVIDIA A100 80GB SXM** using [llama.cpp](https://github.com/ggerganov/llama.cpp)

| File | Size | VRAM | Quality | Best For |
|:-----|:----:|:----:|:-------:|:---------|
| `Pars-Medical-o1-Llama-FFT-Q4_K_M.gguf` | **~2.0 GB** | ~4 GB | ⭐⭐⭐ Good | 💻 Most users, CPU/low VRAM |
| `Pars-Medical-o1-Llama-FFT-Q5_K_M.gguf` | **~2.5 GB** | ~5 GB | ⭐⭐⭐⭐ Better | ⚖️ Balanced quality/speed |
| `Pars-Medical-o1-Llama-FFT-Q8_0.gguf` | **~3.5 GB** | ~6 GB | ⭐⭐⭐⭐⭐ Best | 🎯 High quality inference |

### 💡 Which one to choose? | کدام را انتخاب کنم؟

- **Q4_K_M** → کمترین حجم، مناسب سیستم‌های ضعیف | Smallest, good for low-end systems
- **Q5_K_M** → تعادل بین کیفیت و سرعت | Balance between quality and speed
- **Q8_0** → بهترین کیفیت، نزدیک به مدل اصلی | Best quality, closest to original

---

## 🚀 Quick Start | شروع سریع

### 1️⃣ Ollama (Recommended | پیشنهادی)

```bash
# Direct from HuggingFace
ollama run hf.co/HexQuant/Pars-Medical-o1-Llama-FFT-GGUF

# Or with specific quantization
ollama run hf.co/HexQuant/Pars-Medical-o1-Llama-FFT-GGUF:Q4_K_M
```

### 2️⃣ LM Studio

1. Open LM Studio
2. Go to **Search** tab
3. Search: `HexQuant/Pars-Medical-o1-Llama-FFT-GGUF`
4. Download your preferred quantization
5. Start chatting! 💬

### 3️⃣ llama.cpp

```bash
# Download the model
wget https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT-GGUF/resolve/main/Pars-Medical-o1-Llama-FFT-Q4_K_M.gguf

# Run inference
./llama-cli \
  -m Pars-Medical-o1-Llama-FFT-Q4_K_M.gguf \
  -p "What are the symptoms of diabetes?" \
  -n 512 \
  --temp 0.7
```

### 4️⃣ Python (llama-cpp-python)

```python
from llama_cpp import Llama

# Load model directly from HuggingFace
llm = Llama.from_pretrained(
    repo_id="HexQuant/Pars-Medical-o1-Llama-FFT-GGUF",
    filename="Pars-Medical-o1-Llama-FFT-Q4_K_M.gguf",
    n_ctx=4096,
    n_gpu_layers=-1,  # Use all GPU layers
)

# Chat
response = llm.create_chat_completion(
    messages=[
        {"role": "user", "content": "علائم دیابت نوع ۲ چیست؟"}
    ],
    temperature=0.7,
    max_tokens=512,
)

print(response["choices"][0]["message"]["content"])
```

---

## 💬 Example | نمونه

<details>
<summary><b>🇮🇷 مثال فارسی</b></summary>

**سوال:**
> علائم کم‌کاری تیروئید چیست؟

**پاسخ مدل:**
> `<think>`
> بیایید علائم کم‌کاری تیروئید را بررسی کنیم:
> - کاهش متابولیسم بدن
> - تأثیر بر سیستم‌های مختلف
> `</think>`
>
> علائم اصلی کم‌کاری تیروئید:
> 1. **خستگی مزمن** - احساس کسالت دائمی
> 2. **افزایش وزن** - با وجود رژیم غذایی طبیعی
> 3. **عدم تحمل سرما** - احساس سردی بیشتر
> 4. **یبوست** - کاهش حرکات روده
> 5. **خشکی پوست** - پوست خشک و زبر
> 6. **ریزش مو** - نازک شدن موها

</details>

<details>
<summary><b>🇺🇸 English Example</b></summary>

**Question:**
> What are the warning signs of a heart attack?

**Model Response:**
> `<think>`
> Let me outline the classic and atypical presentations of myocardial infarction.
> `</think>`
>
> **Warning Signs of Heart Attack:**
>
> **Classic Symptoms:**
> 1. Chest pain/pressure (may radiate to arm, jaw, back)
> 2. Shortness of breath
> 3. Cold sweats
> 4. Nausea/vomiting
>
> **Atypical Symptoms (more common in women):**
> - Unusual fatigue
> - Indigestion-like discomfort
> - Dizziness
>
> ⚠️ **If you experience these symptoms, call emergency services immediately!**

</details>

---

## 🔧 Technical Details | جزئیات فنی

| Parameter | Value |
|:----------|:------|
| **Original Model** | [Pars-Medical-o1-Llama-FFT](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT) |
| **Base Architecture** | Llama-3.2-3B-Instruct |
| **Parameters** | 3.2B |
| **Context Length** | 4096 tokens |
| **Quantization Tool** | llama.cpp |
| **Quantization Hardware** | NVIDIA A100 80GB SXM |
| **Languages** | English, Persian (Farsi) |

---

## ⚠️ Disclaimer | سلب مسئولیت

<table>
<tr>
<td width="50%" align="right" dir="rtl">

⚠️ این مدل صرفاً برای **اهداف آموزشی و تحقیقاتی** است.

❌ **جایگزین مشاوره پزشکی حرفه‌ای نیست.**

✅ همیشه با پزشک متخصص مشورت کنید.

</td>
<td width="50%">

⚠️ This model is for **educational and research purposes only**.

❌ **Not a substitute for professional medical advice.**

✅ Always consult with a qualified healthcare provider.

</td>
</tr>
</table>

---

## 🔗 Related Links | لینک‌های مرتبط

| Resource | Link |
|:---------|:-----|
| 🤗 Main Model (BF16) | [Pars-Medical-o1-Llama-FFT](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT) |
| 📦 This Repo (GGUF) | [Pars-Medical-o1-Llama-FFT-GGUF](https://huggingface.co/HexQuant/Pars-Medical-o1-Llama-FFT-GGUF) |
| 🦙 Ollama | [ollama.ai](https://ollama.ai) |
| 💻 LM Studio | [lmstudio.ai](https://lmstudio.ai) |
| 🔧 llama.cpp | [GitHub](https://github.com/ggerganov/llama.cpp) |

---

## 🔗 Connect | ارتباط

<div align="center">

[![Twitter](https://img.shields.io/badge/Twitter-@TheRealPourya-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/TheRealPourya)
[![GitHub](https://img.shields.io/badge/GitHub-xPOURY4-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/xPOURY4)
[![HuggingFace](https://img.shields.io/badge/🤗_HuggingFace-HexQuant-FFD21E?style=for-the-badge)](https://huggingface.co/HexQuant)

---

**Made with ❤️ TheRealPourya**

*If you find this model useful, please ⭐ star the repo and share it!*

</div>