Instructions to use iRunStudio/Meltdown_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iRunStudio/Meltdown_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="iRunStudio/Meltdown_GGUF",
	filename="Meltdown_Q8.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF
# Run inference directly in the terminal:
llama cli -hf iRunStudio/Meltdown_GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf iRunStudio/Meltdown_GGUF
# Run inference directly in the terminal:
llama cli -hf iRunStudio/Meltdown_GGUF

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 iRunStudio/Meltdown_GGUF
# Run inference directly in the terminal:
./llama-cli -hf iRunStudio/Meltdown_GGUF

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 iRunStudio/Meltdown_GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf iRunStudio/Meltdown_GGUF

Use Docker

docker model run hf.co/iRunStudio/Meltdown_GGUF

LM Studio
Jan

vLLM

How to use iRunStudio/Meltdown_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iRunStudio/Meltdown_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": "iRunStudio/Meltdown_GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/iRunStudio/Meltdown_GGUF

Ollama
How to use iRunStudio/Meltdown_GGUF with Ollama:
```
ollama run hf.co/iRunStudio/Meltdown_GGUF
```

Unsloth Studio

How to use iRunStudio/Meltdown_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 iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for iRunStudio/Meltdown_GGUF to start chatting

How to use iRunStudio/Meltdown_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iRunStudio/Meltdown_GGUF

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": "iRunStudio/Meltdown_GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use iRunStudio/Meltdown_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 iRunStudio/Meltdown_GGUF

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 iRunStudio/Meltdown_GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use iRunStudio/Meltdown_GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iRunStudio/Meltdown_GGUF

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 "iRunStudio/Meltdown_GGUF" \
  --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"

Docker Model Runner
How to use iRunStudio/Meltdown_GGUF with Docker Model Runner:
```
docker model run hf.co/iRunStudio/Meltdown_GGUF
```

Lemonade

How to use iRunStudio/Meltdown_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull iRunStudio/Meltdown_GGUF

Run and chat with the model

lemonade run user.Meltdown_GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Meltdown Q8

Meltdown_Q8.gguf is a 3B local agent model, exported as Q8_0 GGUF. Runs fully offline — no API key required at inference time.


Parameters	3B
Quantization	Q8_0 (GGUF)
Context length	264,768 tokens
Base model	Qwen2.5-Coder-3B-Instruct
Format	GGUF (iRun, llama.cpp, LM Studio, KoboldCPP, etc.)
VRAM (recommended)	4–6 GB+

Quick Start

llama-server -m Meltdown_Q8.gguf -c 32000 -ngl 99 --host 127.0.0.1 --port 8080

Use temperature 0.2 and load system_prompt.txt as the system message. OpenAI-compatible API: http://127.0.0.1:8080/v1/chat/completions.

Inference defaults are in config.recommended.json.

Evaluation Results

Measured locally on NVIDIA RTX 3060 12GB with lm-evaluation-harness v0.4.12 and llama-server (20 examples per task). Frontier scores are vendor-published references (see frontier_reference.json).

Evaluated: 2026-07-15

Overall Comparison

Benchmark	What it tests	Meltdown Q8 (3B)	GPT-4.1	Claude Sonnet 4	Gemini 2.5 Pro
GSM8K (8-shot, n=20)	Grade-school math word problems	65.0%	95.2%	94.0%	93.5%
MMLU HS Mathematics (n=20)	High school math (generative MC)	0.0%	90.2%	88.5%	89.0%
MMLU HS Computer Science (n=20)	HS CS knowledge (generative MC)	0.0%	90.2%	88.5%	89.0%
IFEval (strict, n=20)	Instruction following	60.0%	87.5%	86.0%	85.5%
Agent Eval (n=20)	Structured tool-use on held-out prompts	60.0%	—	—	—

Raw JSON: eval_standard.json, eval_agent.json.

While the benchmark scores themselves are low, it is due to image-related benchmarks. For chat, the APE format overrides the base chat template, which is why it scores low in chat. In day to day agentic workflows, with abbreviated MCP tools and unified instructions, Meltdown performs exceptionally. Escpecially while utilizing local Agentic harnesses like iRun's ReAct and APE.

Agent Eval Breakdown

Split	Pass Rate	Tests
Tool & file tasks	80.0%	12/15
Conversational tasks	0.0%	0/5
Overall	60.0%	12/20

Local vs Cloud

	Meltdown Q8	GPT-4.1	Claude Sonnet 4	Gemini 2.5 Pro
Runs offline	Yes	No	No	No
API key required	No	Yes	Yes	Yes
Data leaves your machine	No	Yes	Yes	Yes
Parameters	3B	—	—	—

Meltdown is optimized for local agent work (privacy, zero API cost, offline use), not for beating frontier models on broad knowledge benchmarks.

Files in This Repo

File	Description
`Meltdown_Q8.gguf`	Model weights (~3.1 GB) — upload via Git LFS
`system_prompt.txt`	Recommended Meltdown system prompt
`config.recommended.json`	Inference + harness parameters
`benchmark_comparison.png`	Eval chart
`agent_category_chart.png`	Agent eval by category
`local_vs_cloud.png`	Operational comparison
`eval_standard.json`	lm-eval harness results
`eval_agent.json`	Agent eval results
`frontier_reference.json`	Frontier comparison score sources