How to use from
OpenClaw
Start the llama.cpp server
# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf APRKDEV/icarus-1-3b: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://127.0.0.1:9931/v1 \
  --custom-model-id "APRKDEV/icarus-1-3b: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"
Quick Links

ICARUS-1 3B

Icarus-1 3B is a proprietary deep reasoning kernel engineered from the ground up by Neonaut Studio. It features a custom neural architecture optimized for zero-latency institutional chat and rapid tactical synthesis.

Specifications

  • Architecture: Icarus-1
  • Parameters: 3.0B
  • Precision: Q4_K_M GGUF
  • Context Length: 8,192 Tokens
  • License: Proprietary (Neonaut Studio)

Initiate the Kernel. Control the future.

Downloads last month
16
Safetensors
Model size
3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support