Instructions to use FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-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 FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

LM Studio
Jan
Ollama
How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF with Ollama:
```
ollama run hf.co/FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4
```
Unsloth Desktop

How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4
```

Lemonade

How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Artemis-31B-v1.2-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-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 FaustianDeal/Artemis-31B-v1.2-NVFP4-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://127.0.0.1:8080/v1
hermes config set model.default FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FaustianDeal/Artemis-31B-v1.2-NVFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FaustianDeal/Artemis-31B-v1.2-NVFP4-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://127.0.0.1:8080/v1 \
  --custom-model-id "FaustianDeal/Artemis-31B-v1.2-NVFP4-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"

Artemis 31B v1.2 — NVFP4 GGUF

This is a text-model GGUF conversion of TheDrummer/Artemis-31B-v1.2, a fine-tune of google/gemma-4-31B. The language model's eligible linear weights were calibrated and quantized to NVIDIA NVFP4, then repacked into GGUF. The original fine-tune is credited to TheDrummer; this repository contains a format and precision conversion.

File	Size	SHA-256
`Artemis-31B-v1.2-NVFP4.gguf`	19,313,589,984 bytes (18.0 GiB)	`0892d39cfb7295b07a8890da516cade061c6d4a9ca829bab846586fd831a7917`

Use

Load Artemis-31B-v1.2-NVFP4.gguf as the model in a Gemma 4 and NVFP4-capable GGUF runtime. KoboldCpp 1.121 loaded this file and generated text successfully in a local test. The source model's Gemma 4 chat template is embedded in the GGUF.

Use the Gemma4 31B vision tower if you want image recognition.

Conversion details

Source: TheDrummer/Artemis-31B-v1.2, revision 05d84790fceecefac4ee2adfb7cf33fdce2029f1.
Quantization: LLM Compressor's NVFP4 scheme, with 32 calibration samples of 2,048 tokens from mit-han-lab/pile-val-backup.
Targets: eligible Linear layers. Vision and audio layers, embeddings, and lm_head were excluded from NVFP4 quantization.
GGUF conversion: llama.cpp commit b9ae43a5d4c27564963717281070991fa9b8c1bf, repacking the calibrated NVFP4 checkpoint without a second weight quantization pass.
File inspection: 1,653 tensors, including 410 NVFP4 tensors, 1,242 F32 tensors, and one BF16 tensor. The tokenizer and chat template match the source checkpoint by SHA-256.

Validation and limitations

On the 299-question ARC-Challenge validation split, using zero-shot, letter-only answers in KoboldCpp 1.121, NVFP4 scored 291/299 (97.3%) and a BF16 GGUF from the same v1.2 source scored 293/299 (98.0%). Both returned valid answers for every question; their predictions differed on two questions. This is one direct-answer benchmark run, so the small gap should not be treated as a general quality rating. The compressed-tensors checkpoint has not been benchmarked separately.

Attribution and terms

The original fine-tune is by TheDrummer, based on Gemma 4 31B. Follow the terms that apply to the source fine-tune and base model. The source repository did not declare a license in its model metadata when this card was prepared, so no license is asserted here.