Instructions to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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": "Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M

Ollama
How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF with Ollama:
```
ollama run hf.co/Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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": "Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF with Docker Model Runner:
```
docker model run hf.co/Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M
```

Lemonade

How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-coder-REAP-25B-A3B-Rust-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 "Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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"

Q & A

by Em-80 - opened Jan 24

Discussion

Em-80

Owner Jan 24

If you have any questions, about the quantization options for the ggufs or the imatrix I will answer them as soon as I can. On a first in first out basis.

bobchenyx

Jan 28

Hi there. thanks for the open-source sharing.
I would like to ask what is this model have to do with Rust?
is the optimization only with regarding to imatrix calibration data?

Em-80

Owner Jan 28

•

edited Jan 28

In short the Imatrix was built with thousands of samples of Rust, python, math, and English to map the model weights in order to preserve as much of the Rust/python coding ability through quantization as much as possible. The largest sub-set of the sample data was Rust samples.

bobchenyx

Jan 29

Thanks for the reply.
May I ask, if the calibration dataset would be open-source at some point?
or if not. are you using pure safe rust with no unsafe block?

Em-80

Owner Jan 29

•

edited Jan 30

Alright so the rust part of the data sample was pulled from the stack overflow rust data set. And importantly the Imatrix isn't a fine toon just a preservation mechanism. The data set used by Alibaba and Cerberus is gonna effect the output of the model way more then my Imatrix. I built a map using data samples to not crush important weights while quantizing to preserve the models rust ability as much as possible. Long story short the way Imatrix works as long as the sample activates the rust expert and weights the model had it gets mapped. You want unsafe and safe to trigger model weights to preserve them. Imatrix doesn't train it preserves. For this use case of imatrix you want safe,unsafe,incomplete,good and bad examples in the sample to activate weights for both fixing and generating code. I'm not giving out my exact sample set with this repo. This is a model repo not a data-set repo.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment