Instructions to use Blazed-Forge/Testing-Grounds-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blazed-Forge/Testing-Grounds-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Blazed-Forge/Testing-Grounds-GGUF",
	filename="Versipellis-v2-Q5_K_S.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Blazed-Forge/Testing-Grounds-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S
# Run inference directly in the terminal:
llama-cli -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S
# Run inference directly in the terminal:
llama-cli -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

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 Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S
# Run inference directly in the terminal:
./llama-cli -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

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 Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

Use Docker

docker model run hf.co/Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

LM Studio
Jan
Ollama
How to use Blazed-Forge/Testing-Grounds-GGUF with Ollama:
```
ollama run hf.co/Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S
```

Unsloth Studio

How to use Blazed-Forge/Testing-Grounds-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Blazed-Forge/Testing-Grounds-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Blazed-Forge/Testing-Grounds-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Blazed-Forge/Testing-Grounds-GGUF to start chatting

How to use Blazed-Forge/Testing-Grounds-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Blazed-Forge/Testing-Grounds-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

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 Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Blazed-Forge/Testing-Grounds-GGUF with Docker Model Runner:
```
docker model run hf.co/Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S
```

Lemonade

How to use Blazed-Forge/Testing-Grounds-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Blazed-Forge/Testing-Grounds-GGUF:Q5_K_S

Run and chat with the model

lemonade run user.Testing-Grounds-GGUF-Q5_K_S

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Blazed Forge

🔥 TESTING GROUNDS 🔨

"Hot off the anvil!"

Ateron and Nimbz tinkering the next merge into shape.

🛠️ What This Is

As the name implies, this is the room for fresh-out-the-oven merges of the Blazed Forge. This repo holds GGUF to unreleased merges - they are brand-new and not yet proven, polished, or promised to behave. You gotta find that out for yourself here!

If a build survives our testing, it gets cleaned up and moved out to its own proper repo. Until then, it lives on the workbench over here, waiting for brave testers.

🔒 Locked Access

This repository is locked to the public — only invited testers can pull these builds.

If you want to apply, please get in touch with us over the BeaverAI Discord or through opening a new discussion. Thanks!

— 🔨 ⚒️ 🔥 ⚒️ 🔨 —

Downloads last month: 145

GGUF

Model size

32B params

Architecture

gemma4

Hardware compatibility

5-bit

Inference Providers NEW

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

Collection including Blazed-Forge/Testing-Grounds-GGUF

Want to test not-yet released models first?

Collection

1 item • Updated 13 days ago