# Quick Llama
[](https://badge.fury.io/py/quick-llama)
[](https://pepy.tech/project/quick-llama)
[](https://opensource.org/licenses/MIT)
[](https://github.com/nuhmanpk/quick-llama/graphs/contributors)
[](https://github.com/nuhmanpk/quick-llama/commits)
[](https://pypi.org/project/quick-llama/)
A Python wrapper for Ollama that simplifies managing and interacting with LLMs on colab with multi model and reasoning model support.
<p align="center">
<img src="https://raw.githubusercontent.com/nuhmanpk/quick-llama/main/images/llama-image.webp" width="300" height="300" />
</p>
QuickLlama automates server setup, model management, and seamless interaction with LLMs, providing an effortless developer experience.
🚀 Colab-Ready: Easily run and experiment with QuickLlama on Google Colab for hassle-free, cloud-based development!
> **Note**: Don’t forget to use a GPU if you actually want it to perform well!
## Installtion
```sh
pip install quick-llama
```
```sh
!pip install quick-llama
```
### Serve a model
```py
from quick_llama import QuickLlama
model = 'gemma3'
quick_llama = QuickLlama(model_name=model,verbose=True)
quick_llama.init() # -> starts the server in background
```
### Serve QuickLlama
```py
from quick_llama import QuickLlama
from ollama import chat
from ollama import ChatResponse
# Defaults to gemma3
model = 'gemma3'
quick_llama = QuickLlama(model_name=model,verbose=True)
quick_llama.init()
response: ChatResponse = chat(model=model, messages=[
{
'role': 'user',
'content': 'Why is the sky blue?',
},
])
print(response['message']['content'])
# or access fields directly from the response object
print(response.message.content)
quick_llama.stop()
```
## MultiModels
```py
import requests
import os
from ollama import chat
from quick_llama import QuickLlama
model = 'gemma3'
quick_llama = QuickLlama(model_name=model,verbose=True)
quick_llama.init()
# Step 1: Download the image
img_url = "https://raw.githubusercontent.com/nuhmanpk/quick-llama/main/images/llama-image.webp" # quick llama cover photo
img_path = "temp_llama_image.webp"
with open(img_path, "wb") as f:
f.write(requests.get(img_url).content)
# Step 2: Send the image to the model
response = chat(
model=model,
messages=[
{
"role": "user",
"content": "Describe what you see in this photo.",
"images": [img_path],
}
]
)
# Step 3: Print the result
print(response['message']['content'])
# Step 4: Clean up the image file
os.remove(img_path)
```
```py
from quick_llama import QuickLlama
from ollama import chat
from ollama import ChatResponse
# Defaults to gemma3
quick_llama = QuickLlama(model_name="gemma3")
quick_llama.init()
response: ChatResponse = chat(model='gemma3', messages=[
{
'role': 'user',
'content': 'what is 6 times 5?',
},
])
print(response['message']['content'])
print(response.message.content)
```
## Use with Langchain
```py
from quick_llama import QuickLlama
from langchain_ollama import OllamaLLM
model_name = "gemma3"
quick_llama = QuickLlama(model_name=model_name,verbose=True)
quick_llama.init()
model = OllamaLLM(model=model_name)
model.invoke("Come up with 10 names for a song about parrots")
```
## Use custom Models
```py
quick_llama = QuickLlama() # Defaults to mistral
quick_llama.init()
# Custom Model
# Supports all models from https://ollama.com/search
quick_llama = QuickLlama(model_name="custom-model-name")
quick_llama.init()
```
## List Models
```py
quick_llama.list_models()
```
## Stop Model
```py
quick_llama.stop_model("gemma3")
```
## Stop Server
```py
quick_llama.stop()
```
Made with ❤️ by [Nuhman](https://github.com/nuhmanpk). Happy Coding 🚀
Raw data
{
"_id": null,
"home_page": "https://github.com/nuhmanpk/quick-llama",
"name": "quick-llama",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ollama llama3 colab ai open-source openai llm quick-llama",
"author": "Nuhman PK",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/c9/bf/bdfe5532a0ad7bc1a7b5cc113643a358b0e9a722041cc11e4ef19221ae05/quick_llama-0.1.0.tar.gz",
"platform": null,
"description": "# Quick Llama\n\n[](https://badge.fury.io/py/quick-llama)\n[](https://pepy.tech/project/quick-llama)\n[](https://opensource.org/licenses/MIT)\n[](https://github.com/nuhmanpk/quick-llama/graphs/contributors)\n[](https://github.com/nuhmanpk/quick-llama/commits)\n[](https://pypi.org/project/quick-llama/)\n\n\nA Python wrapper for Ollama that simplifies managing and interacting with LLMs on colab with multi model and reasoning model support.\n\n<p align=\"center\">\n <img src=\"https://raw.githubusercontent.com/nuhmanpk/quick-llama/main/images/llama-image.webp\" width=\"300\" height=\"300\" />\n</p>\n\nQuickLlama automates server setup, model management, and seamless interaction with LLMs, providing an effortless developer experience.\n\n\ud83d\ude80 Colab-Ready: Easily run and experiment with QuickLlama on Google Colab for hassle-free, cloud-based development!\n\n> **Note**: Don\u2019t forget to use a GPU if you actually want it to perform well!\n\n## Installtion\n\n```sh\npip install quick-llama\n```\n\n```sh\n!pip install quick-llama\n```\n\n### Serve a model\n```py\nfrom quick_llama import QuickLlama\nmodel = 'gemma3'\nquick_llama = QuickLlama(model_name=model,verbose=True)\n\nquick_llama.init() # -> starts the server in background\n```\n\n### Serve QuickLlama\n\n```py\nfrom quick_llama import QuickLlama\n\nfrom ollama import chat\nfrom ollama import ChatResponse\n\n# Defaults to gemma3\nmodel = 'gemma3'\nquick_llama = QuickLlama(model_name=model,verbose=True)\n\nquick_llama.init()\n\nresponse: ChatResponse = chat(model=model, messages=[\n {\n 'role': 'user',\n 'content': 'Why is the sky blue?',\n },\n])\nprint(response['message']['content'])\n# or access fields directly from the response object\nprint(response.message.content)\n\nquick_llama.stop()\n\n```\n\n## MultiModels\n```py\nimport requests\nimport os\nfrom ollama import chat\nfrom quick_llama import QuickLlama\n\nmodel = 'gemma3'\nquick_llama = QuickLlama(model_name=model,verbose=True)\n\nquick_llama.init()\n\n# Step 1: Download the image\nimg_url = \"https://raw.githubusercontent.com/nuhmanpk/quick-llama/main/images/llama-image.webp\" # quick llama cover photo\nimg_path = \"temp_llama_image.webp\"\n\nwith open(img_path, \"wb\") as f:\n f.write(requests.get(img_url).content)\n\n# Step 2: Send the image to the model\nresponse = chat(\n model=model,\n messages=[\n {\n \"role\": \"user\",\n \"content\": \"Describe what you see in this photo.\",\n \"images\": [img_path],\n }\n ]\n)\n\n# Step 3: Print the result\nprint(response['message']['content'])\n\n# Step 4: Clean up the image file\nos.remove(img_path)\n\n```\n\n\n```py\nfrom quick_llama import QuickLlama\n\n\nfrom ollama import chat\nfrom ollama import ChatResponse\n\n# Defaults to gemma3\nquick_llama = QuickLlama(model_name=\"gemma3\")\n\nquick_llama.init()\n\nresponse: ChatResponse = chat(model='gemma3', messages=[\n {\n 'role': 'user',\n 'content': 'what is 6 times 5?',\n },\n])\nprint(response['message']['content'])\n\nprint(response.message.content)\n```\n\n## Use with Langchain \n\n```py\nfrom quick_llama import QuickLlama\nfrom langchain_ollama import OllamaLLM\n\nmodel_name = \"gemma3\"\n\nquick_llama = QuickLlama(model_name=model_name,verbose=True)\n\nquick_llama.init()\n\nmodel = OllamaLLM(model=model_name)\nmodel.invoke(\"Come up with 10 names for a song about parrots\")\n```\n\n## Use custom Models\n\n```py\nquick_llama = QuickLlama() # Defaults to mistral\nquick_llama.init()\n\n# Custom Model\n# Supports all models from https://ollama.com/search\nquick_llama = QuickLlama(model_name=\"custom-model-name\")\nquick_llama.init()\n```\n## List Models\n\n```py\nquick_llama.list_models()\n```\n\n## Stop Model\n```py\nquick_llama.stop_model(\"gemma3\")\n```\n## Stop Server\n\n```py\nquick_llama.stop()\n```\n\n\nMade with \u2764\ufe0f by [Nuhman](https://github.com/nuhmanpk). Happy Coding \ud83d\ude80\n",
"bugtrack_url": null,
"license": null,
"summary": "Run Ollama models easily, anywhere \u2013 including online platforms like Google Colab",
"version": "0.1.0",
"project_urls": {
"Documentation": "https://github.com/nuhmanpk/quick-llama/blob/main/README.md",
"Funding": "https://github.com/sponsors/nuhmanpk",
"Homepage": "https://github.com/nuhmanpk/quick-llama",
"Source": "https://github.com/nuhmanpk/quick-llama/",
"Tracker": "https://github.com/nuhmanpk/quick-llama/issues"
},
"split_keywords": [
"ollama",
"llama3",
"colab",
"ai",
"open-source",
"openai",
"llm",
"quick-llama"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "1b550d948c4185071a9e56ede698e22568f502fa0e57664eb37e94801c0b6228",
"md5": "4f08c12f3023b50526acda5d5e464c23",
"sha256": "c27ca5d7fcca85dc86cd76d4179ea9bb532b6b4c4f83f8772a920f44b08ed610"
},
"downloads": -1,
"filename": "quick_llama-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4f08c12f3023b50526acda5d5e464c23",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 5616,
"upload_time": "2025-07-08T12:34:21",
"upload_time_iso_8601": "2025-07-08T12:34:21.222112Z",
"url": "https://files.pythonhosted.org/packages/1b/55/0d948c4185071a9e56ede698e22568f502fa0e57664eb37e94801c0b6228/quick_llama-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "c9bfbdfe5532a0ad7bc1a7b5cc113643a358b0e9a722041cc11e4ef19221ae05",
"md5": "338aaa97bbbc8e28f9a9a94f95abe684",
"sha256": "af7a95d730e43a520b6dae0a4e592bad917f23e354a634012f14bb4c0f8c15b5"
},
"downloads": -1,
"filename": "quick_llama-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "338aaa97bbbc8e28f9a9a94f95abe684",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 5300,
"upload_time": "2025-07-08T12:34:22",
"upload_time_iso_8601": "2025-07-08T12:34:22.009713Z",
"url": "https://files.pythonhosted.org/packages/c9/bf/bdfe5532a0ad7bc1a7b5cc113643a358b0e9a722041cc11e4ef19221ae05/quick_llama-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-08 12:34:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nuhmanpk",
"github_project": "quick-llama",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "quick-llama"
}
JSON
