Instructions to use AtomicChat/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 AtomicChat/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 AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
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 AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
Use Docker
docker model run hf.co/AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use AtomicChat/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 "AtomicChat/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": "AtomicChat/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/AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
- Ollama
How to use AtomicChat/Inkling-2-Mini-GGUF with Ollama:
ollama run hf.co/AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use AtomicChat/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 AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
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": "AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use AtomicChat/Inkling-2-Mini-GGUF with Docker Model Runner:
docker model run hf.co/AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
- Lemonade
How to use AtomicChat/Inkling-2-Mini-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Inkling-2-Mini-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use AtomicChat/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 AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
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 AtomicChat/Inkling-2-Mini-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AtomicChat/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 AtomicChat/Inkling-2-Mini-GGUF: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 "AtomicChat/Inkling-2-Mini-GGUF: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"
Commit History
Today
-
Card: link the Uncensored LoRA
Verified signaturecaabd64
Yesterday
-
Card: AD-IQ2_S measured; the Q8_0 ceiling note
Verified signature591ada2 -
AD-Q6_K (full imatrix, 9291 chunks)
Verified signature6b1bd09 -
Card: the whole AD ladder measured (IQ2_S pending)
Verified signature5bb2954 -
AD-Q5_K (full imatrix, 9291 chunks)
Verified signaturebefb65f -
AD-IQ4_XS (full imatrix, 9291 chunks)
Verified signaturee4e3101 -
AD-IQ2_S (full imatrix, 9291 chunks)
Verified signature88b14ff -
AD-Q4_K (full imatrix, 9291 chunks)
Verified signature90e1167 -
AD-IQ3_S (full imatrix, 9291 chunks)
Verified signature7d47812 -
AD-IQ2_M (full imatrix, 9291 chunks)
Verified signature4405dbd -
Card: AD ladder so far with KLD and top-1, presets as the baseline
Verified signatured0bab88 -
AD-IQ2_XXS (full imatrix, 9291 chunks)
Verified signaturee456fb3 -
Card: AD-IQ3_XXS and AD-IQ2_XXS-Q2
Verified signaturecba34e8 -
Card: AD-IQ1_S measured
Verified signaturecf1f9d3 -
Card: final AD-IQ1 files (full imatrix), AD-IQ1_M measured
Verified signatureba0a586 -
AD-IQ1_S (full imatrix, 9291 chunks)
Verified signature3400102 -
AD-IQ2_XXS-Q2 (full imatrix, 9291 chunks)
Verified signature1e6d957 -
AD-IQ3_XXS (full imatrix, 9291 chunks)
Verified signaturea5aa85b -
AD-IQ1_M (full imatrix, 9291 chunks)
Verified signatureea3b2bb -
AD-IQ1_S: restore the early file of f50b0d8a (2688 chunks), overwritten by mistake at 22:15
Verified signatureedb8f2d -
AD-IQ1_M, 7.26 GB (early imatrix; replaced by the full-imatrix file under the same name)
Verified signaturec10e084 -
AD-IQ1_S, early imatrix (1360 of 9291 chunks); the full-imatrix file replaces it
Verified signaturec410322 -
Card: early AD-IQ1_S and AD-IQ1_M
Verified signature11a7d4e -
AD-IQ1_S, 6.88 GB (early imatrix, 2688 chunks; replaced by the full-imatrix file under the same name)
Verified signaturef50b0d8 -
Card: the real expert down types of each preset
Verified signature150a934 -
Card: BF16, Q8_0, presets and mmproj are up; how to run on PR #32695
Verified signature7778d3e -
BF16 (exact dequantization of the vendor NVFP4/MXFP8 checkpoint), 2 parts
Verified signature78639d3 -
Q4_K_M (llama.cpp preset, no imatrix)
Verified signature76657a6 -
Q5_K_M (llama.cpp preset, no imatrix)
Verified signature9ae687a -
Q6_K (llama.cpp preset, no imatrix)
Verified signature9b4844e -
Q8_0 (llama.cpp preset, no imatrix)
Verified signaturefee5fab -
pipeline: mmproj-Inkling-2-Mini-BF16.gguf
Verified signature4fb6317 -
pipeline: mmproj-Inkling-2-Mini-F16.gguf
Verified signature8eef0cc -
card: Atomic Chat, Discord, GitHub and X buttons; Atomic Chat bullet
Verified signaturea720a44 -
Apache-2.0 license of the base model
Verified signaturea72d1aa -
Card: status while the files are built
Verified signature8e7f2ae -
initial commit
Verified signatureea35f4d