Instructions to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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": "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

SGLang

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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": "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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": "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with Ollama:
```
ollama run hf.co/Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M
```

Unsloth Studio

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 Spakie/SmolLM3-3B-DeepSeek-V4-Q4-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 Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF to start chatting

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with Docker Model Runner:
```
docker model run hf.co/Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M
```

Lemonade

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM3-3B-DeepSeek-V4-Q4-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

SmolLM-3B-DeepSeek-V4 (GGUF Q4_K_M)

A fine-tuned version of SmolLM3-3B trained on a distillation dataset generated from DeepSeek V4 Pro, quantized to Q4_K_M GGUF for local inference.

File: SmolLM3-3B-4bit.Q4_K_M.gguf — 1.92 GB

Training Details

Base model: HuggingFaceTB/SmolLM3-3B
Fine-tuning method: Supervised Fine-Tuning (SFT)
Dataset: DeepSeek V4 Pro distill (datasets/Spakie/DeepSeek-V4-Pro-distill-V2)
Hardware: Apple M5 Max (128GB unified memory)
Framework: MLX / Unsloth Studio

Usage

llama.cpp

llama serve -hf Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF

Ollama

ollama run hf.co/Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF

llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF",
    filename="SmolLM3-3B-4bit.Q4_K_M.gguf",
)
llm.create_chat_completion(
    messages=[{"role": "user", "content": "Explain what a transformer is."}]
)

Performance

No evals run yet on this fine-tune. Refer to the base model card for SmolLM3-3B benchmark results (may be innaccurate).

Limitations

May reflect stylistic patterns from the distillation source
Not independently evaluated for safety or bias beyond the base model
Generated content may be factually inaccurate; verify important outputs
No tool calling support (planned for V2)

License

Apache 2.0 (inherited from base model). Fine-tuning dataset is not released.

Downloads last month: 115

GGUF

Model size

3B params

Architecture

smollm3

Hardware compatibility

4-bit

Model tree for Spakie/SmolLM3-3B-DeepSeek-V4-Q4-GGUF

Base model

HuggingFaceTB/SmolLM3-3B-Base

Finetuned

HuggingFaceTB/SmolLM3-3B

Quantized

(109)

this model