Instructions to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF with Ollama:
```
ollama run hf.co/ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ImposterOnline/Pyrex-8B-Instruct-Uncensored-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": "ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M
```

Lemonade

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Pyrex-8B-Instruct-Uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ImposterOnline/Pyrex-8B-Instruct-Uncensored-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 "ImposterOnline/Pyrex-8B-Instruct-Uncensored-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"

Pyrex-8B-Instruct-Uncensored GGUF

Quantized builds for Pyrex-8B-Instruct-Uncensored.

File	Size	Notes
`pyrex-f16.gguf`	15.2 GB	Full precision
`pyrex-q4_k_m.gguf`	4.4 GB	Recommended daily driver
`pyrex-q5_k_m.gguf`	5.1 GB	Higher quality
`pyrex-q8_0.gguf`	8.1 GB	Best quality

Chat format: chatml (<|im_start|> tokens).

Architecture: Pyrex 8B Transformer (original design)

Benchmarks (Verified on Kaggle T4 GPU)

Benchmark	Score
HumanEval	87.20%
MBPP	6.23%
SWE Debugging	100%

# Ollama
ollama create pyrex-8b -f Modelfile
ollama run pyrex-8b "Write a Python function to implement quicksort."

# llama.cpp
./llama-cli -m pyrex-q4_k_m.gguf -p "<|im_start|>user
Write a C++ thread pool.
<|im_end|>
<|im_start|>assistant
" -n 512 -c 8192

Pyrex is an independent project for high-performance, uncensored engineering assistance.

Downloads last month: 616

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

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