Instructions to use ikarius/Mistral-Small-24B-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ikarius/Mistral-Small-24B-NF4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ikarius/Mistral-Small-24B-NF4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ikarius/Mistral-Small-24B-NF4")
model = AutoModelForCausalLM.from_pretrained("ikarius/Mistral-Small-24B-NF4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ikarius/Mistral-Small-24B-NF4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ikarius/Mistral-Small-24B-NF4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ikarius/Mistral-Small-24B-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ikarius/Mistral-Small-24B-NF4

SGLang

How to use ikarius/Mistral-Small-24B-NF4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ikarius/Mistral-Small-24B-NF4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ikarius/Mistral-Small-24B-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ikarius/Mistral-Small-24B-NF4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ikarius/Mistral-Small-24B-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ikarius/Mistral-Small-24B-NF4 with Docker Model Runner:
```
docker model run hf.co/ikarius/Mistral-Small-24B-NF4
```

Mistral-Small-24B-NF4

This repository contains a 4-bit quantized version of Mistral-Small-24B, optimized with NF4 (NormalFloat 4) via bitsandbytes. This version is designed to run efficiently on consumer hardware (GPUs with less VRAM) without significant performance loss.

Model Description

Mistral-Small-24B is a powerful language model that balances reasoning capabilities and speed. Using NF4 quantization reduces the model size to approximately 14.2 GB, making it available for setups with 16GB or 24GB VRAM.

Architecture: Mistral
Precision: 4-bit (NF4)
Quantization method: bitsandbytes
Format: Safetensors

Installation and usage

To use this model you need transformers, bitsandbytes and accelerate.

pip install -U transformers bitsandbytes accelerate

Example of use (Python)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "ikarius/Mistral-Small-24B-NF4"

# Load the model with NF4 configuration
model = AutoModelForCausalLM.from_pretrained( 
model_id, 
device_map="auto", 
torch_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)

# Simple chat test
messages = [ 
{"role": "user", "content": "Hi! Can you explain the benefit of NF4 quantization?"}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=200)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Files in this repository

model.safetensors: The actual model weights in 4-bit format.
config.json & generation_config.json: Configuration files for model architecture and generation.
tokenizer.json & tokenizer_config.json: Tokenizer settings for correct text processing.
chat_template.jinja: Template for formatting chats (Instruct format).

License

Please see the original Mistral-Small guidelines for terms of use. This model is distributed assuming the user follows the Mistral AI license agreement.

Downloads last month: 18

Safetensors

Model size

24B params

Tensor type

F32

BF16

Model tree for ikarius/Mistral-Small-24B-NF4

Base model

mistralai/Mistral-Small-24B-Base-2501

Finetuned

mistralai/Mistral-Small-24B-Instruct-2501

Quantized

(108)

this model