Instructions to use nace-ai/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 nace-ai/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 nace-ai/Inkling-2-Mini-GGUF:NVFP4 # Run inference directly in the terminal: llama cli -hf nace-ai/Inkling-2-Mini-GGUF:NVFP4
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf nace-ai/Inkling-2-Mini-GGUF:NVFP4 # Run inference directly in the terminal: llama cli -hf nace-ai/Inkling-2-Mini-GGUF:NVFP4
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 nace-ai/Inkling-2-Mini-GGUF:NVFP4 # Run inference directly in the terminal: ./build/bin/llama cli -hf nace-ai/Inkling-2-Mini-GGUF:NVFP4
Use Docker
docker model run hf.co/nace-ai/Inkling-2-Mini-GGUF:NVFP4
- Llama new
- LM Studio
- Jan
- Ollama
How to use nace-ai/Inkling-2-Mini-GGUF with Ollama:
ollama run hf.co/nace-ai/Inkling-2-Mini-GGUF:NVFP4
- Unsloth Desktop
- Pi
How to use nace-ai/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 nace-ai/Inkling-2-Mini-GGUF:NVFP4
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": "nace-ai/Inkling-2-Mini-GGUF:NVFP4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use nace-ai/Inkling-2-Mini-GGUF with Docker Model Runner:
docker model run hf.co/nace-ai/Inkling-2-Mini-GGUF:NVFP4
- Lemonade
How to use nace-ai/Inkling-2-Mini-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull nace-ai/Inkling-2-Mini-GGUF:NVFP4
Run and chat with the model
lemonade run user.Inkling-2-Mini-GGUF-NVFP4
List all available models
lemonade list
- Hermes Agent
How to use nace-ai/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 nace-ai/Inkling-2-Mini-GGUF:NVFP4
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 nace-ai/Inkling-2-Mini-GGUF:NVFP4
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use nace-ai/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 nace-ai/Inkling-2-Mini-GGUF:NVFP4
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 "nace-ai/Inkling-2-Mini-GGUF:NVFP4" \ --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"
Inkling-2-Mini-GGUF
Nace.AI weight conversions of Inkling 2 Mini.
Results
Held-out split. Mean KL against Original checkpoint weights ยท BF16 activations, over 2,040 scored token positions. Lower is closer.
KL uses llama.cpp scaled-uint16 reference probabilities and includes base log-probabilities above -16.
| Artifact | Size, GB | Bits/weight | Mean KL |
|---|---|---|---|
| Nace NVFP4 | 19.103 | 5.862 | 0.004 |
Sizes cover each text-backbone GGUF file. Vision and MTP are omitted. Sizes use decimal GB. Uncertainty intervals are not plotted.
Scores and method ยท Chart data
Reference
Original NVFP4/MXFP8 weights are decoded with FP32 scale arithmetic and rounded to BF16 GEMM operands, with no affine requantization or activation QDQ. Torch BF16 linear operations return BF16; the CUDA backend uses FP32 accumulation with reduced-precision BF16 reductions disabled. Routing gamma is applied after the down projection; routed expert outputs are accumulated in FP32 and returned as BF16. Original FP32 controllers and routing are retained; the ordinary BF16 head output is widened before FP32 softcap. FP32 matmul TF32 is disabled. This is official HF eager text execution, not native W4A4/source-QDQ or cross-engine bitwise parity.
Method
Matching native expert blocks keep the same weights as the official checkpoint and are repacked without requantization. Native-block round-trip check scope: sampled original NVFP4 rows, exact scale-inclusive dequantization after gate/up permutation; all global scales compared; eight lossy MXFP8-to-Q8_0 tensors excluded. Q8_0 fallback tensors: blk.20.ffn_gate_up_exps.weight, blk.20.ffn_down_exps.weight, blk.21.ffn_gate_up_exps.weight, blk.21.ffn_down_exps.weight, blk.22.ffn_gate_up_exps.weight, blk.22.ffn_down_exps.weight, blk.23.ffn_gate_up_exps.weight, blk.23.ffn_down_exps.weight. The native-block check does not cover the requantized fallback tensors.
Run
Build the CUDA runtime from llama.cpp PR #32704 at the pinned commit.
git clone https://github.com/ggml-org/llama.cpp.git
git -C llama.cpp fetch origin refs/pull/32704/head
git -C llama.cpp checkout 2a28df0f9bd55c4975b6bffb35229a6020720f13
cmake -S llama.cpp -B llama.cpp/build -DGGML_CUDA=ON -DGGML_METAL=OFF
cmake --build llama.cpp/build --config Release -j
llama.cpp/build/bin/llama-cli -hf nace-ai/Inkling-2-Mini-GGUF \
--hf-file Inkling-2-Mini-NVFP4.gguf \
-p "Explain binary search." -n 256
License
Apache 2.0. Original model by Thinking Machines Lab, Inc. See NOTICE and the source model card for attribution and its linked use policy.
- Downloads last month
- -
4-bit
Model tree for nace-ai/Inkling-2-Mini-GGUF
Base model
thinkingmachines/Inkling-2-Mini