Instructions to use smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smarttasks/SmolLM3-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/smarttasks/SmolLM3-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use smarttasks/SmolLM3-3B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/smarttasks/SmolLM3-3B-GGUF:Q4_K_M

Ollama
How to use smarttasks/SmolLM3-3B-GGUF with Ollama:
```
ollama run hf.co/smarttasks/SmolLM3-3B-GGUF:Q4_K_M
```

Unsloth Studio

How to use smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use smarttasks/SmolLM3-3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smarttasks/SmolLM3-3B-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": "smarttasks/SmolLM3-3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use smarttasks/SmolLM3-3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smarttasks/SmolLM3-3B-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 "smarttasks/SmolLM3-3B-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 smarttasks/SmolLM3-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/smarttasks/SmolLM3-3B-GGUF:Q4_K_M
```

Lemonade

How to use smarttasks/SmolLM3-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smarttasks/SmolLM3-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM3-3B-GGUF-Q4_K_M

List all available models

lemonade list

SmolLM3-3B-GGUF / MANIFEST.json

roenb

Upload folder using huggingface_hub

4d1d67e verified 16 days ago

Raw

History Blame Contribute Delete

4.13 kB

	{
	"schema": "smarttasks.repo_manifest/v1",
	"generated_utc": "2026-07-17T09:36:04+00:00",
	"root": "SmolLM3-3B-GGUF",
	"file_count": 14,
	"risk_finding_count": 0,
	"classes_present": [
	"binary",
	"contextual",
	"ingestible",
	"model"
	],
	"agent_prefilter_hint": {
	"load": [
	"contextual",
	"ingestible"
	],
	"runtime_only": [
	"model"
	],
	"never_auto_execute": [
	"executable"
	],
	"quarantine": [
	"sensitive"
	]
	},
	"files": [
	{
	"path": ".gitattributes",
	"bytes": 43,
	"content_class": "binary",
	"ingest_policy": "skip",
	"sha256": "4cf00e98dded8779b234ba8d2356ce03ef5360f69632bd81f0f10c4c944b89d9",
	"risk_findings": []
	},
	{
	"path": "README.md",
	"bytes": 12034,
	"content_class": "contextual",
	"ingest_policy": "load_as_context",
	"sha256": "08be054bd03d225b1b689c2ec6bfad750f72771e25e7b50eefc2f97e7d544dfd",
	"risk_findings": []
	},
	{
	"path": "SECURITY.md",
	"bytes": 2007,
	"content_class": "contextual",
	"ingest_policy": "load_as_context",
	"sha256": "4d1dad4d1dbf5e3c2b7673d042198c4da9d2bfb8e2e6ba3405532581a1e839cf",
	"risk_findings": []
	},
	{
	"path": "SHA256SUMS",
	"bytes": 352,
	"content_class": "binary",
	"ingest_policy": "skip",
	"sha256": "64b16295d75e207b6a7c497a5c9b3a524a4e26aab5097be8dba7b024a7bfc519",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B-Q4_K_M.gguf",
	"bytes": 1915305888,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "bf342c11ef16312997beaa48068c4e1b5a319ce83873c9602e1a6a4a01eaa8d2",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B-Q4_K_M.transparency.json",
	"bytes": 42765,
	"content_class": "ingestible",
	"ingest_policy": "load_structured",
	"sha256": "b32fe1e1ed87c10f27be6789f4f230cb5d319e70af2aed7114ec11f4bbf469ef",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B-Q4_K_M.transparency_report.md",
	"bytes": 5419,
	"content_class": "contextual",
	"ingest_policy": "load_as_context",
	"sha256": "abd7dec3ba483c79d2e736fc332cd1fc543c42dd501344b0e4824a4a4b9542ac",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B-Q5_K_M.gguf",
	"bytes": 2213756832,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "bfc86eac71b5a1ace9fc99568967a570642483b2fcfd616607101127537e97fb",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B-Q6_K.gguf",
	"bytes": 2530860960,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "4c9c3292a5ad3f4d11e49e372d7b2caa7eab32e66fc15306d42317a0e4ae6392",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B-Q8_0.gguf",
	"bytes": 3275575200,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "f2a892115b8a850ea8542e3d487a940c9d811eb7e3d57c1603543db6f63dfd89",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B.security_digest.json",
	"bytes": 1629,
	"content_class": "ingestible",
	"ingest_policy": "load_structured",
	"sha256": "09e8d8c363765a836350587818c04840d1db97bbaa1a4facfe59215186505600",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B.speed.json",
	"bytes": 3048,
	"content_class": "ingestible",
	"ingest_policy": "load_structured",
	"sha256": "a046f5261001c336f91fcf584367cf2110ffb008061ba1e857ba71438c857a2b",
	"risk_findings": []
	},
	{
	"path": "SmolLM3-3B.speed.md",
	"bytes": 941,
	"content_class": "contextual",
	"ingest_policy": "load_as_context",
	"sha256": "03c91b8317b061a1cf960b2b42d290fb67669bc3993f80423f34b3c1580a909e",
	"risk_findings": []
	},
	{
	"path": "scorecard.json",
	"bytes": 10230,
	"content_class": "ingestible",
	"ingest_policy": "load_structured",
	"sha256": "fef654a52b51a1cf85c760d0fb62f04df8ad957df61a6d29e7d4dab42fe81df0",
	"risk_findings": []
	}
	]
	}