Instructions to use iRunStudio/Meltdown_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 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

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

Hermes Agent

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

Meltdown_GGUF / frontier_reference.json

iRunStudio

MeltDown V1-GGUF

28788d0 verified 23 days ago

Raw

History Blame Contribute Delete

5.2 kB

	{
	"meta": {
	"updated": "2026-07-15",
	"note": "Frontier scores are vendor-published or leaderboard-reported numbers for comparison only. Meltdown is a 3B local agent model — compare on the right axes (agent/tool-calling, latency, cost, privacy), not raw MMLU vs 200B+ models.",
	"score_format": "percentage (0-100) unless noted"
	},
	"benchmarks": {
	"humaneval": {
	"label": "HumanEval (pass@1)",
	"category": "code",
	"models": {
	"meltdown_q8": { "score": null, "params": "3B", "source": "run benchmarks/run_standard.ps1" },
	"qwen2.5_coder_3b_instruct": { "score": 70.1, "params": "3B", "source": "Qwen2.5-Coder technical report (Nov 2024)" },
	"gpt_4_1": { "score": 92.0, "params": "~", "source": "OpenAI GPT-4.1 announcement (Apr 2025)" },
	"claude_sonnet_4": { "score": 90.2, "params": "~", "source": "Anthropic Claude Sonnet 4 model card" },
	"gemini_2_5_pro": { "score": 89.0, "params": "~", "source": "Google Gemini 2.5 Pro benchmarks" }
	}
	},
	"mbpp": {
	"label": "MBPP (pass@1)",
	"category": "code",
	"models": {
	"meltdown_q8": { "score": null, "params": "3B", "source": "run benchmarks/run_standard.ps1" },
	"qwen2.5_coder_3b_instruct": { "score": 68.4, "params": "3B", "source": "Qwen2.5-Coder technical report" },
	"gpt_4_1": { "score": 88.5, "params": "~", "source": "OpenAI GPT-4.1 announcement" },
	"claude_sonnet_4": { "score": 87.0, "params": "~", "source": "Anthropic Claude Sonnet 4 model card" },
	"gemini_2_5_pro": { "score": 86.5, "params": "~", "source": "Google Gemini 2.5 Pro benchmarks" }
	}
	},
	"gsm8k": {
	"label": "GSM8K (8-shot)",
	"category": "math",
	"models": {
	"meltdown_q8": { "score": null, "params": "3B", "source": "run benchmarks/run_standard.ps1" },
	"qwen2.5_coder_3b_instruct": { "score": 67.5, "params": "3B", "source": "Qwen2.5-Coder technical report" },
	"gpt_4_1": { "score": 95.2, "params": "~", "source": "OpenAI GPT-4.1 announcement" },
	"claude_sonnet_4": { "score": 94.0, "params": "~", "source": "Anthropic Claude Sonnet 4 model card" },
	"gemini_2_5_pro": { "score": 93.5, "params": "~", "source": "Google Gemini 2.5 Pro benchmarks" }
	}
	},
	"mmlu": {
	"label": "MMLU (5-shot)",
	"category": "knowledge",
	"models": {
	"meltdown_q8": { "score": null, "params": "3B", "source": "run benchmarks/run_standard.ps1" },
	"qwen2.5_coder_3b_instruct": { "score": 65.9, "params": "3B", "source": "Qwen2.5-Coder technical report" },
	"gpt_4_1": { "score": 90.2, "params": "~", "source": "OpenAI GPT-4.1 announcement" },
	"claude_sonnet_4": { "score": 88.5, "params": "~", "source": "Anthropic Claude Sonnet 4 model card" },
	"gemini_2_5_pro": { "score": 89.0, "params": "~", "source": "Google Gemini 2.5 Pro benchmarks" }
	}
	},
	"ifeval": {
	"label": "IFEval (strict)",
	"category": "instruction",
	"models": {
	"meltdown_q8": { "score": null, "params": "3B", "source": "run benchmarks/run_standard.ps1" },
	"qwen2.5_coder_3b_instruct": { "score": 55.0, "params": "3B", "source": "Qwen2.5-Coder technical report (approx)" },
	"gpt_4_1": { "score": 87.5, "params": "~", "source": "OpenAI GPT-4.1 announcement" },
	"claude_sonnet_4": { "score": 86.0, "params": "~", "source": "Anthropic Claude Sonnet 4 model card" },
	"gemini_2_5_pro": { "score": 85.5, "params": "~", "source": "Google Gemini 2.5 Pro benchmarks" }
	}
	},
	"bfcl_v3_overall": {
	"label": "BFCL v3 Overall (tool calling)",
	"category": "agent",
	"models": {
	"meltdown_q8": { "score": null, "params": "3B", "source": "run benchmarks/run_bfcl.ps1" },
	"qwen2.5_coder_3b_instruct": { "score": 72.0, "params": "3B", "source": "BFCL leaderboard (approx)" },
	"gpt_4_1": { "score": 88.0, "params": "~", "source": "BFCL leaderboard" },
	"claude_sonnet_4": { "score": 87.5, "params": "~", "source": "BFCL leaderboard" },
	"gemini_2_5_pro": { "score": 86.0, "params": "~", "source": "BFCL leaderboard" }
	}
	},
	"ape_compliance": {
	"label": "APE Protocol Compliance",
	"category": "agent",
	"models": {
	"meltdown_q8": { "score": 68.0, "params": "3B", "source": "benchmarks/run_agent_eval.py (harness-aware, n=50 stratified)" },
	"qwen2.5_coder_3b_instruct": { "score": null, "params": "3B", "source": "N/A — not APE-trained" },
	"gpt_4_1": { "score": null, "params": "~", "source": "N/A — not APE-trained" },
	"claude_sonnet_4": { "score": null, "params": "~", "source": "N/A — not APE-trained" },
	"gemini_2_5_pro": { "score": null, "params": "~", "source": "N/A — not APE-trained" }
	}
	}
	},
	"display_names": {
	"meltdown_q8": "Meltdown Q8 (3B)",
	"qwen2.5_coder_3b_instruct": "Qwen2.5-Coder-3B (base)",
	"gpt_4_1": "GPT-4.1",
	"claude_sonnet_4": "Claude Sonnet 4",
	"gemini_2_5_pro": "Gemini 2.5 Pro"
	},
	"comparison_models": [
	"meltdown_q8",
	"gpt_4_1",
	"claude_sonnet_4",
	"gemini_2_5_pro"
	]
	}