GGUF
conversational
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 ggml-org-dev/small-test:F16
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 "ggml-org-dev/small-test:F16" \
  --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

Test fixture for the llama.cpp server CI: a ~95M Qwen3.5 based VLM covering chat, tool calling, OCR and MTP drafting.

Model card, HF weights and training pipeline: https://huggingface.co/Serveurperso/small-test

Downloads last month
49
GGUF
Model size
94.9M params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ggml-org-dev/small-test

Quantized
(1)
this model