Instructions to use cortexso/mistral-small-24b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/mistral-small-24b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/mistral-small-24b",
	filename="mistral-small-24b-base-2501-q2_k.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cortexso/mistral-small-24b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/mistral-small-24b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/mistral-small-24b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/mistral-small-24b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/mistral-small-24b:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf cortexso/mistral-small-24b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/mistral-small-24b:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf cortexso/mistral-small-24b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/mistral-small-24b:Q4_K_M

Use Docker

docker model run hf.co/cortexso/mistral-small-24b:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/mistral-small-24b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/mistral-small-24b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/mistral-small-24b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cortexso/mistral-small-24b:Q4_K_M

Ollama
How to use cortexso/mistral-small-24b with Ollama:
```
ollama run hf.co/cortexso/mistral-small-24b:Q4_K_M
```

Unsloth Studio

How to use cortexso/mistral-small-24b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cortexso/mistral-small-24b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cortexso/mistral-small-24b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/mistral-small-24b to start chatting

Docker Model Runner
How to use cortexso/mistral-small-24b with Docker Model Runner:
```
docker model run hf.co/cortexso/mistral-small-24b:Q4_K_M
```

Lemonade

How to use cortexso/mistral-small-24b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/mistral-small-24b:Q4_K_M

Run and chat with the model

lemonade run user.mistral-small-24b-Q4_K_M

List all available models

lemonade list

jan-hq commited on Jan 31, 2025

Commit

1044a8d

verified ·

1 Parent(s): 2648d59

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +25 -0

README.md ADDED Viewed

	@@ -0,0 +1,25 @@

+---
+license: mit
+---
+## Overview
+Mistral-Small-24B is a lightweight and efficient AI model designed for natural language processing tasks, leveraging the foundational architecture of Mistral-Small-24B-Base-2501. Its primary purpose is to deliver fast and accurate text generation, comprehension, and interaction capabilities across various applications. Ideal use cases include chatbots, content creation, summarization, and language translation, making it suitable for both personal and enterprise-level solutions. With its smaller size, Mistral-Small-24B provides a balance between performance and resource efficiency, allowing implementation on devices with limited computational power. This model has demonstrated strong performance metrics, ensuring quality outputs and responsiveness comparable to larger models, while maintaining reduced latency and operational costs.
+## Variants
+| No | Variant | Cortex CLI command |
+| --- | --- | --- |
+| 1 | [gguf](https://huggingface.co/cortexso/mistral-small-24b-base-2501/tree/main) | cortex run mistral-small-24b-base-2501 |
+## Use it with Jan (UI)
+1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
+2. Use in Jan model Hub:
+    cortexso/mistral-small-24b-base-2501
+## Use it with Cortex (CLI)
+1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
+2. Run the model with command:
+    cortex run mistral-small-24b-base-2501
+## Credits
+- **Author:** mistralai
+- **Converter:** [Homebrew](https://www.homebrew.ltd/)
+- **Original License:** [License](#)