Instructions to use DoppelReflEx/MiniusLight-24B-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DoppelReflEx/MiniusLight-24B-v3 with Transformers:

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

pipe = pipeline("text-generation", model="DoppelReflEx/MiniusLight-24B-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/MiniusLight-24B-v3")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/MiniusLight-24B-v3", 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 DoppelReflEx/MiniusLight-24B-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DoppelReflEx/MiniusLight-24B-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DoppelReflEx/MiniusLight-24B-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DoppelReflEx/MiniusLight-24B-v3

SGLang

How to use DoppelReflEx/MiniusLight-24B-v3 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 "DoppelReflEx/MiniusLight-24B-v3" \
    --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": "DoppelReflEx/MiniusLight-24B-v3",
		"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 "DoppelReflEx/MiniusLight-24B-v3" \
        --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": "DoppelReflEx/MiniusLight-24B-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DoppelReflEx/MiniusLight-24B-v3 with Docker Model Runner:
```
docker model run hf.co/DoppelReflEx/MiniusLight-24B-v3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiniusLight-24B-v3

12B - 24B-v1 - 24B-v1.01 - 24B-v2 - 24B-v2.1 - 24B-v3

Origin Content (Click Here)

What is this?

Maybe this is last 24B Mistral model of this series. I'm tired (laugh).

Thanks for two base models, this model archive very good styles and consistency in long context. 30th test btw, that mean there are 29 models fail to find and create this model.

Best model of the series (for me). :)

GGUF

Static - iMatrix

Other information

Chat Template? Mistral V7 - Tekken. ChatML are also good to use, but Mistral V7 - Tekken is recommend

Merge Method

Detail YAML Config

  {
  models:
    - model: TheDrummer/Cydonia-24B-v4.1
    - model: Delta-Vector/Rei-24B-KTO
  merge_method: slerp
  base_model: TheDrummer/Cydonia-24B-v4.1
  parameters:
    t: [0.1, 0.2, 0.3, 0.5, 0.8, 0.5, 0.3, 0.2, 0.1]
  dtype: bfloat16
  tokenizer_source: base
  }

Downloads last month: 10

Safetensors

Model size

24B params

Tensor type

BF16

Model tree for DoppelReflEx/MiniusLight-24B-v3

Delta-Vector/Rei-24B-KTO

TheDrummer/Cydonia-24B-v4.1

Merge model

this model

Quantizations

3 models

Collection including DoppelReflEx/MiniusLight-24B-v3

Nocturne

Collection

Balance size model with good quality. • 6 items • Updated Sep 11, 2025 • 1

DoppelReflEx
/

MiniusLight-24B-v3

MiniusLight-24B-v3

12B - 24B-v1 - 24B-v1.01 - 24B-v2 - 24B-v2.1 - 24B-v3

What is this?

GGUF

Static - iMatrix

Other information

Chat Template? Mistral V7 - Tekken. ChatML are also good to use, but Mistral V7 - Tekken is recommend

Merge Method

Detail YAML Config

{ models: - model: TheDrummer/Cydonia-24B-v4.1 - model: Delta-Vector/Rei-24B-KTO merge_method: slerp base_model: TheDrummer/Cydonia-24B-v4.1 parameters: t: [0.1, 0.2, 0.3, 0.5, 0.8, 0.5, 0.3, 0.2, 0.1] dtype: bfloat16 tokenizer_source: base }

Model tree for DoppelReflEx/MiniusLight-24B-v3

Collection including DoppelReflEx/MiniusLight-24B-v3

Nocturne

MiniusLight-24B-v3

12B - 24B-v1 - 24B-v1.01 - 24B-v2 - 24B-v2.1 - 24B-v3

What is this?

GGUF

Static - iMatrix

Other information

Chat Template? Mistral V7 - Tekken. ChatML are also good to use, but Mistral V7 - Tekken is recommend

Merge Method

Detail YAML Config { models: - model: TheDrummer/Cydonia-24B-v4.1 - model: Delta-Vector/Rei-24B-KTO merge_method: slerp base_model: TheDrummer/Cydonia-24B-v4.1 parameters: t: [0.1, 0.2, 0.3, 0.5, 0.8, 0.5, 0.3, 0.2, 0.1] dtype: bfloat16 tokenizer_source: base }

Model tree for DoppelReflEx/MiniusLight-24B-v3

Collection including DoppelReflEx/MiniusLight-24B-v3

Detail YAML Config

{ models: - model: TheDrummer/Cydonia-24B-v4.1 - model: Delta-Vector/Rei-24B-KTO merge_method: slerp base_model: TheDrummer/Cydonia-24B-v4.1 parameters: t: [0.1, 0.2, 0.3, 0.5, 0.8, 0.5, 0.3, 0.2, 0.1] dtype: bfloat16 tokenizer_source: base }