Instructions to use APRKDEV/icarus-1-70b-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use APRKDEV/icarus-1-70b-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="APRKDEV/icarus-1-70b-Q4_K_M-GGUF",
	filename="icarus-1-70b-Q4_K_M.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 APRKDEV/icarus-1-70b-Q4_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf APRKDEV/icarus-1-70b-Q4_K_M-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 APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf APRKDEV/icarus-1-70b-Q4_K_M-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 APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use APRKDEV/icarus-1-70b-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "APRKDEV/icarus-1-70b-Q4_K_M-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": "APRKDEV/icarus-1-70b-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M

Ollama
How to use APRKDEV/icarus-1-70b-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use APRKDEV/icarus-1-70b-Q4_K_M-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 APRKDEV/icarus-1-70b-Q4_K_M-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 APRKDEV/icarus-1-70b-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for APRKDEV/icarus-1-70b-Q4_K_M-GGUF to start chatting

Docker Model Runner
How to use APRKDEV/icarus-1-70b-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use APRKDEV/icarus-1-70b-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull APRKDEV/icarus-1-70b-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.icarus-1-70b-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Icarus-1 70B Flagship [GGUF]

Icarus-1 70B is the flagship reasoning kernel of the Icarus lineage, synthesized for heavy logic, deep mathematical deduction, and high-fidelity code generation. This repository contains the optimized GGUF weights, specifically quantized for high-performance local inference.

Specifications

Lineage: Icarus (Text & Reasoning)
Parameters: 70.6B
Quantization: Q4_K_M (High performance, minimal logic loss)
Base Kernel: Icarus-1 70B Heavy Reasoning Kernel
Identity Protocol: Neonaut Sovereign Purification

Quantization Details

This distribution was synthesized using a high-performance build of the GGUF toolchain. The Q4_K_M format was selected as the optimal balance for reasoning tasks, providing 4-bit quantization for most tensors while maintaining higher precision for critical attention and feed-forward layers.

Deployment

This model is best utilized with GGUF-compatible backends.

# Example Inference
./icarus-cli -m icarus_70b_Q4_K_M.gguf -p "Analyze the following logical paradox..."

Downloads last month: 26

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

4-bit