Instructions to use reecdev/Tiny3.5-Coder-500M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use reecdev/Tiny3.5-Coder-500M 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 reecdev/Tiny3.5-Coder-500M:F16
# Run inference directly in the terminal:
llama cli -hf reecdev/Tiny3.5-Coder-500M:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf reecdev/Tiny3.5-Coder-500M:F16
# Run inference directly in the terminal:
llama cli -hf reecdev/Tiny3.5-Coder-500M:F16

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 reecdev/Tiny3.5-Coder-500M:F16
# Run inference directly in the terminal:
./llama-cli -hf reecdev/Tiny3.5-Coder-500M:F16

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 reecdev/Tiny3.5-Coder-500M:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf reecdev/Tiny3.5-Coder-500M:F16

Use Docker

docker model run hf.co/reecdev/Tiny3.5-Coder-500M:F16

LM Studio
Jan
Ollama
How to use reecdev/Tiny3.5-Coder-500M with Ollama:
```
ollama run hf.co/reecdev/Tiny3.5-Coder-500M:F16
```
Unsloth Desktop

How to use reecdev/Tiny3.5-Coder-500M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reecdev/Tiny3.5-Coder-500M:F16

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": "reecdev/Tiny3.5-Coder-500M:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use reecdev/Tiny3.5-Coder-500M with Docker Model Runner:
```
docker model run hf.co/reecdev/Tiny3.5-Coder-500M:F16
```

Lemonade

How to use reecdev/Tiny3.5-Coder-500M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull reecdev/Tiny3.5-Coder-500M:F16

Run and chat with the model

lemonade run user.Tiny3.5-Coder-500M-F16

List all available models

lemonade list

Hermes Agent

How to use reecdev/Tiny3.5-Coder-500M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reecdev/Tiny3.5-Coder-500M:F16

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 reecdev/Tiny3.5-Coder-500M:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use reecdev/Tiny3.5-Coder-500M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reecdev/Tiny3.5-Coder-500M:F16

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 "reecdev/Tiny3.5-Coder-500M:F16" \
  --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"

Tiny3.5

An attempt to compress Qwen3.5 into 500M and 1.5B parameters.

What is this?

Tiny3.5 is my community effort to create tiny and more efficient versions of Qwen3.5. The strengths of Tiny3.5 include very low inference latency, minimal overthinking, and being able to run on much weaker hardware. However, it's important to realize that Tiny3.5 is sub-2B parameters. Don't expect a 99% score on every single benchmark.

How is this better than Qwen3.5?

Tiny3.5 uses many techniques to produce better efficiency than Qwen3.5 in many scenarios. We use multi-shot distillation to filter out pointless reasoning loops and improve the overall quality of responses.

Can I create my own model using the Tiny3.5 dataset?

Absolutely! Our distillation dataset is open-source, and the code used to create it alongside a copy of the dataset is available on our GitHub: https://github.com/reecdev/tiny3.5

Downloads last month: 10

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for reecdev/Tiny3.5-Coder-500M

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B

Quantized

(43)

this model

reecdev
/

Tiny3.5-Coder-500M

Tiny3.5

What is this?

How is this better than Qwen3.5?

Can I create my own model using the Tiny3.5 dataset?

Model tree for reecdev/Tiny3.5-Coder-500M

Dataset used to train reecdev/Tiny3.5-Coder-500M