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

Libraries

How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with Transformers:

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

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

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

llama-cpp-python

How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bobchenyx/DeepSeek-V3-0324-MLA-GGUF",
	filename="DeepSeek-V3-0324-MLA-IQ1_M/DeepSeek-V3-0324-MLA-IQ1_M-00001-of-00009.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bobchenyx/DeepSeek-V3-0324-MLA-GGUF: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 bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bobchenyx/DeepSeek-V3-0324-MLA-GGUF: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 bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M

SGLang

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

Ollama
How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with Ollama:
```
ollama run hf.co/bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M
```

Unsloth Studio new

How to use bobchenyx/DeepSeek-V3-0324-MLA-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 bobchenyx/DeepSeek-V3-0324-MLA-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 bobchenyx/DeepSeek-V3-0324-MLA-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with Docker Model Runner:
```
docker model run hf.co/bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M
```

Lemonade

How to use bobchenyx/DeepSeek-V3-0324-MLA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bobchenyx/DeepSeek-V3-0324-MLA-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-V3-0324-MLA-GGUF-Q4_K_M

List all available models

lemonade list

How to use from the

Use from the

llama-cpp-python library

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bobchenyx/DeepSeek-V3-0324-MLA-GGUF",
	filename="",
)

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

llama.cpp Quantizations of DeepSeek-V3-0324 (MLA version)

This page is going to be deprecated. For other quantized versions, please refer to moxin-org/DeepSeek-V3-0324-Moxin-GGUF for more details.

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

- IQ1_S : 129.94 GiB (1.66 BPW)
- IQ1_M : 144.24 GiB (1.85 BPW)
- Q2_K_L : 222.01 GiB (2.84 BPW)
- Q4_K_L : 381.64 GiB (4.89 BPW)

Smallest Compression (103GB)

For our smallest compressed version. Please refer to tflsxyy/DeepSeek-V3-0324-E192 and bobchenyx/DeepSeek-V3-0324-508B-A32B-MLA-GGUF for more details.

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 = "bobchenyx/DeepSeek-V3-0324-MLA-GGUF",
    local_dir = "bobchenyx/DeepSeek-V3-0324-MLA-GGUF",
    allow_patterns = ["*IQ1_M*"],
)

Downloads last month: 9

GGUF

Model size

671B params

Architecture

deepseek2

Hardware compatibility

1-bit

2-bit

4-bit

Model tree for bobchenyx/DeepSeek-V3-0324-MLA-GGUF

Base model

deepseek-ai/DeepSeek-V3-0324

Quantized

(25)

this model

Collection including bobchenyx/DeepSeek-V3-0324-MLA-GGUF

DeepSeek-MoE

Collection

DeepseekV3ForCausalLM • 3 items • Updated Dec 1, 2025