Instructions to use stneric/simplixity-writer-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 stneric/simplixity-writer-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 stneric/simplixity-writer-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf stneric/simplixity-writer-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 stneric/simplixity-writer-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf stneric/simplixity-writer-4b-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf stneric/simplixity-writer-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf stneric/simplixity-writer-4b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/stneric/simplixity-writer-4b-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use stneric/simplixity-writer-4b-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/stneric/simplixity-writer-4b-GGUF:Q4_K_M

Ollama
How to use stneric/simplixity-writer-4b-GGUF with Ollama:
```
ollama run hf.co/stneric/simplixity-writer-4b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use stneric/simplixity-writer-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 stneric/simplixity-writer-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": "stneric/simplixity-writer-4b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use stneric/simplixity-writer-4b-GGUF with Docker Model Runner:
```
docker model run hf.co/stneric/simplixity-writer-4b-GGUF:Q4_K_M
```

Lemonade

How to use stneric/simplixity-writer-4b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stneric/simplixity-writer-4b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.simplixity-writer-4b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use stneric/simplixity-writer-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 stneric/simplixity-writer-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 stneric/simplixity-writer-4b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use stneric/simplixity-writer-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 stneric/simplixity-writer-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 "stneric/simplixity-writer-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"

simplixity-writer-4b-GGUF

GGUF files of simplixity-writer-4b, the answer model of Simplixity. Results, limits and training are described there.

File	Size
`simplixity-writer-4b-v1-Q4_K_M.gguf`	2.8 GB	recommended
`simplixity-writer-4b-v1-Q8_0.gguf`	4.6 GB

Both files keep the MTP layer, so Ollama and llama.cpp can use it for speculative decoding (about 127 → 180 tokens/s on an RTX 3070 Ti).

Use with Ollama

Save this as Modelfile, with the full path to the downloaded file:

FROM /full/path/to/simplixity-writer-4b-v1-Q4_K_M.gguf
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER num_ctx 8192
PARAMETER draft_num_predict 2

Then run:

ollama create simplixity-writer:4b-v1-q4_k_m -f Modelfile

RENDERER and PARSER: without them, the system prompt never reaches the model.
num_ctx: the window the model was trained for. Simplixity reads it from Ollama and fits the sources to it.
draft_num_predict 2: turns on speculative decoding with the MTP layer in Ollama 0.40 and newer. 3 is slower.
The path after FROM: a relative path does not work.

In Simplixity, choose simplixity-writer:4b-v1-q4_k_m as the chat model with provider Ollama.

Use with llama.cpp

llama-server -m simplixity-writer-4b-v1-Q4_K_M.gguf -c 8192 --spec-type draft-mtp --spec-draft-n-max 2

Licence

Apache 2.0, like the base model.

Downloads last month: 168

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

Model tree for stneric/simplixity-writer-4b-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

stneric/simplixity-writer-4b

Quantized

(2)

this model