Instructions to use sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use sylvester-francis/rust-mentor-4b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sylvester-francis/rust-mentor-4b-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": "sylvester-francis/rust-mentor-4b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M

Ollama
How to use sylvester-francis/rust-mentor-4b-GGUF with Ollama:
```
ollama run hf.co/sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use sylvester-francis/rust-mentor-4b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sylvester-francis/rust-mentor-4b-GGUF with Docker Model Runner:
```
docker model run hf.co/sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M
```

Lemonade

How to use sylvester-francis/rust-mentor-4b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.rust-mentor-4b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-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 sylvester-francis/rust-mentor-4b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sylvester-francis/rust-mentor-4b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sylvester-francis/rust-mentor-4b-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 "sylvester-francis/rust-mentor-4b-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"

RustMentor 4B — GGUF (Q4_K_M)

A Rust programming tutor fine-tuned from Gemma 3 4B-IT. Teaches Rust by drawing comparisons to Python, Go, and TypeScript.

Model Details


Base model	google/gemma-3-4b-it
Fine-tuning	QLoRA (r=16, alpha=16) via Unsloth + TRL
Quantization	Q4_K_M (k-quant mixed precision via llama.cpp)
Size	~2.5 GB
Format	GGUF (compatible with llama.cpp, PocketPal AI, Maid)
License	Gemma

Intended Use

Offline Android coding tutor for developers learning Rust. The model:

Explains Rust concepts using parallels to Python, Go, and TypeScript
Covers ownership, borrowing, lifetimes, traits, error handling, async, and more
Refuses out-of-domain questions (non-Rust topics)
Resists prompt injection attempts

How to Run

PocketPal AI (Android): Download from the Play Store, then load this model from the HF Hub.

llama.cpp (CLI):

./llama-cli -m rust-mentor-4b-Q4_K_M.gguf -p "<start_of_turn>user
Explain ownership in Rust<end_of_turn>
<start_of_turn>model
"

Training Data

Fine-tuned on 500 samples covering:

16 Rust teaching conversations (ownership, borrowing, lifetimes, traits, enums, pattern matching, async, iterators, structs, strings, serde, cargo, error handling, testing, memory model)
10 out-of-domain refusal examples (Java, C++, Ruby, cooking, math, etc.)
9 prompt injection hardening examples (persona override, instruction extraction, jailbreak roleplay, encoded bypass, etc.)

Limitations

Focused exclusively on Rust — will refuse other programming languages
Comparisons are anchored to Python, Go, and TypeScript only
4B model may occasionally produce less precise answers than 8B+ models
Q4_K_M quantization may reduce quality on nuanced reasoning tasks

Downloads last month: 179

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for sylvester-francis/rust-mentor-4b-GGUF

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(491)

this model