Instructions to use noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama cli -hf noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE

Use Docker

docker model run hf.co/noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE

Llama new
LM Studio
Jan

vLLM

How to use noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE

Ollama
How to use noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF with Ollama:
```
ollama run hf.co/noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE
```
Unsloth Desktop
Docker Model Runner
How to use noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE
```

Lemonade

How to use noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF:MXFP4_MOE

Run and chat with the model

lemonade run user.DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF-MXFP4_MOE

List all available models

lemonade list

Atomic Chat

This is a MXFP4_MOE quantization of the model DeepSeek-MoE-16B-Chat

Original model: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat

Downloads last month: 127

GGUF

Model size

16B params

Architecture

deepseek

Hardware compatibility

4-bit

Model tree for noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF

Base model

deepseek-ai/deepseek-moe-16b-chat

Quantized

(17)

this model