Instructions to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="moxin-org/DeepSeek-V3-0324-Moxin-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("moxin-org/DeepSeek-V3-0324-Moxin-GGUF", dtype="auto")

llama-cpp-python

How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="moxin-org/DeepSeek-V3-0324-Moxin-GGUF",
	filename="V3-IQ1_M/DeepSeek-V3-0324-Moxin-IQ1_M-00001-of-00006.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use moxin-org/DeepSeek-V3-0324-Moxin-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 moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_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 moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_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 moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M

Use Docker

docker model run hf.co/moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moxin-org/DeepSeek-V3-0324-Moxin-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": "moxin-org/DeepSeek-V3-0324-Moxin-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M

SGLang

How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF 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 "moxin-org/DeepSeek-V3-0324-Moxin-GGUF" \
    --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": "moxin-org/DeepSeek-V3-0324-Moxin-GGUF",
		"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 "moxin-org/DeepSeek-V3-0324-Moxin-GGUF" \
        --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": "moxin-org/DeepSeek-V3-0324-Moxin-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with Ollama:
```
ollama run hf.co/moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M
```

Unsloth Studio

How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF 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 moxin-org/DeepSeek-V3-0324-Moxin-GGUF 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 moxin-org/DeepSeek-V3-0324-Moxin-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for moxin-org/DeepSeek-V3-0324-Moxin-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with Docker Model Runner:
```
docker model run hf.co/moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M
```

Lemonade

How to use moxin-org/DeepSeek-V3-0324-Moxin-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull moxin-org/DeepSeek-V3-0324-Moxin-GGUF:IQ1_M

Run and chat with the model

lemonade run user.DeepSeek-V3-0324-Moxin-GGUF-IQ1_M

List all available models

lemonade list

Moxin x llama.cpp Customized Quant for DeepSeek-V3-0324

All quants made based on moxin-org/CC-MoE.

IQ1_M is based on recipes defined via the --tensor-type option.

IQ1_S is a more dynamic version intended for extreme compression.

Q2_K_L is a specialized version with only 2/4/8 bit quant designed for personalized deployment and experiments.

- IQ1_S : 137.66 GiB (1.76 BPW)
- IQ1_M : 151.25 GiB (1.94 BPW)
- Q2_K_L : 210.60 GiB (2.70 BPW)

👈 Download Guide

# !pip install huggingface_hub hf_transfer
import os
# os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id = "moxin-org/DeepSeek-V3-0324-Moxin-GGUF",
    local_dir = "DeepSeek-V3-0324-Moxin-GGUF",
    allow_patterns = ["*IQ1_M*"], # Q2_K_L, IQ1_S, Mini
)

Download Available for huggingface_hub, huggingface-cli, snapshot_download, xet.

Benchmark Comparison

Benchmark (Metric)	llamacpp IQ1_M (140G)	llamacpp Q2_K (230G)	Ours IQ1_S (138G)	Ours IQ1_M (152G)
Winogrande	73.00	77.74	78.69	79.48
MMLU (EM)	75.45	85.57	85.42	86.07
CMMLU	77.06	82.57	86.65	87.84
Hellaswag	78.70	86.46	85.39	85.94
gsm8k	83.40	93.40	93.93	94.39
BBH	24.68	69.19	84.95	86.87

Note: All models use MoE architecture with 37B activated and 671B total parameters.
Bold values mark the best performance per benchmark.

Usage

Example of runing gguf with local build of llama.cpp. (llama-cli/llama-server)

👈 Build llama.cpp locally

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp

cmake -B build -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
cmake --build build --config Release -j --clean-first

build/bin/llama-cli -m DeepSeek-V3-0324-Moxin-GGUF/V3-IQ1_M/DeepSeek-V3-0324-Moxin-IQ1_M-00001-of-00006.gguf \
  -ngl 99 \
  --temp 0.3 \
  --min-p 0.01 \
  --ctx-size 8192 \ # 4096, 16384

Smallest Compression (CC-MoE)

For our smallest compressed version 105.58 GiB (1.79 BPW). Please refer to tflsxyy/DeepSeek-V3-0324-E192 and V3-Mini-Exp for more details.

Citation

If this work is helpful, please kindly cite as:

@article{chen2025collaborative,
  title={Collaborative Compression for Large-Scale MoE Deployment on Edge},
  author={Chen, Yixiao and Xie, Yanyue and Yang, Ruining and Jiang, Wei and Wang, Wei and He, Yong and Chen, Yue and Zhao, Pu and Wang, Yanzhi},
  journal={arXiv preprint arXiv:2509.25689},
  year={2025}
}