Instructions to use ggml-org/Inkling-2-Mini-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ggml-org/Inkling-2-Mini-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 ggml-org/Inkling-2-Mini-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf ggml-org/Inkling-2-Mini-GGUF:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/Inkling-2-Mini-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf ggml-org/Inkling-2-Mini-GGUF:BF16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ggml-org/Inkling-2-Mini-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf ggml-org/Inkling-2-Mini-GGUF:BF16
Use Docker
docker model run hf.co/ggml-org/Inkling-2-Mini-GGUF:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use ggml-org/Inkling-2-Mini-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ggml-org/Inkling-2-Mini-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": "ggml-org/Inkling-2-Mini-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/ggml-org/Inkling-2-Mini-GGUF:BF16
- Ollama
How to use ggml-org/Inkling-2-Mini-GGUF with Ollama:
ollama run hf.co/ggml-org/Inkling-2-Mini-GGUF:BF16
- Unsloth Desktop
- Pi
How to use ggml-org/Inkling-2-Mini-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ggml-org/Inkling-2-Mini-GGUF:BF16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ggml-org/Inkling-2-Mini-GGUF:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ggml-org/Inkling-2-Mini-GGUF with Docker Model Runner:
docker model run hf.co/ggml-org/Inkling-2-Mini-GGUF:BF16
- Lemonade
How to use ggml-org/Inkling-2-Mini-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ggml-org/Inkling-2-Mini-GGUF:BF16
Run and chat with the model
lemonade run user.Inkling-2-Mini-GGUF-BF16
List all available models
lemonade list
- Hermes Agent
How to use ggml-org/Inkling-2-Mini-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 ggml-org/Inkling-2-Mini-GGUF:BF16
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://127.0.0.1:9931/v1 hermes config set model.default ggml-org/Inkling-2-Mini-GGUF:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ggml-org/Inkling-2-Mini-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ggml-org/Inkling-2-Mini-GGUF:BF16
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/Inkling-2-Mini-GGUF:BF16" \ --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"
original repo thinkingmachines Inkling-2-Mini has only 19.5gb model
original repo thinkingmachines Inkling-2-Mini has only 19.5gb model file, so from where is coming your 'full' 52.2gb model?
can you directly convert original 19.5gb file to gguf?
original repo thinkingmachines Inkling-2-Mini has only 19.5gb model file, so from where is coming your 'full' 52.2gb model?
It says so in the readme.
The NVFP4 and MXFP8 experts of the checkpoint are stored as BF16
that not makes 19.5gb full precision (52.2gb)
The BF16 is an upcast.
The original release model is quanized, as stated. But it is simpler to expand it to eg bf16 first, before requantizing it to eg iq4_nl.
The iq4_nl is pretty close in size and which tensor has how many bytes to the original release.
I can guess that, But. if it is upcast problem arises about comparing between quantized models and 'full' (which is up-cast?).
e.g. here AtomicChat/Inkling-2-Mini-GGUF lot of KDL mesurements against base.. but if it is up-cast, is not it silly?
same at Unsloth..
Why is measuring how much you diverge silly?
it is about calling up-cast weights 'original'.
It doesn't.
Original precision. The NVFP4 and MXFP8 experts of the checkpoint are stored as BF16
Original precision is not Original weights
Original precision is not Original weights
Exactly 😉
I just modified the BF16 row to clarify, it now reads:
| BF16 | 52.2 GB | 16-bit precision. The NVFP4 and MXFP8 experts of the original checkpoint are upcast to BF16 |
As others have commented, the original weights are distributed using NVFP4 and MXFP8 for the experts.
and? my statement is: KDL mesurements against up-cast / not-original BF16 weights is silly(not academic word). should be mentioned original-quantized weights.
Inkling 2 Mini was trained with 4-bit precision, which we describe in a recent article on Connectionism. We use 4-bit NVFP4 precision in the expert layers on all forward passes from pretraining through RL, bolstered by a dedicated kernel and hardware-accelerated on NVIDIA’s GB300 platform. The final 4 layers’ forward passes ran in 8-bit (MXFP8).
Inkling 2 Mini’s weights are deployed in the same numeric precision they were trained on—20 layers in NVFP4 and 4 in MXFP8—so there is no conversion loss from quantization.
https://thinkingmachines.ai/news/inkling-2-mini/#nvfp4-and-low-bit-quantization