Instructions to use locailabs/Jupiter-G-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use locailabs/Jupiter-G-8B-GGUF with Transformers:

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("locailabs/Jupiter-G-8B-GGUF")
model = AutoModelForImageTextToText.from_pretrained("locailabs/Jupiter-G-8B-GGUF")

llama-cpp-python

How to use locailabs/Jupiter-G-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="locailabs/Jupiter-G-8B-GGUF",
	filename="models--locailabs--Jupiter-G-8B-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use locailabs/Jupiter-G-8B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M

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 locailabs/Jupiter-G-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M

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 locailabs/Jupiter-G-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/locailabs/Jupiter-G-8B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use locailabs/Jupiter-G-8B-GGUF with Ollama:
```
ollama run hf.co/locailabs/Jupiter-G-8B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use locailabs/Jupiter-G-8B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for locailabs/Jupiter-G-8B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for locailabs/Jupiter-G-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for locailabs/Jupiter-G-8B-GGUF to start chatting

Pi new

How to use locailabs/Jupiter-G-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf locailabs/Jupiter-G-8B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "locailabs/Jupiter-G-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use locailabs/Jupiter-G-8B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf locailabs/Jupiter-G-8B-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://127.0.0.1:8080/v1
hermes config set model.default locailabs/Jupiter-G-8B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use locailabs/Jupiter-G-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/locailabs/Jupiter-G-8B-GGUF:Q4_K_M
```

Lemonade

How to use locailabs/Jupiter-G-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull locailabs/Jupiter-G-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Jupiter-G-8B-GGUF-Q4_K_M

List all available models

lemonade list

Jupiter-G-8B

Jupiter-G-8B is a post-trained variant of Google Gemma 4 E4B IT, developed by Locai Labs. The G denotes the Gemma base. Jupiter-G-8B improves instruction following (+1.7 IFEval, +1.0 IFBench) and coding/agentic capability (+3.2 LCB pass@1) while preserving the base model's reasoning and knowledge through our Forget-Me-Not™ framework. This model was trained on 1 H200 GPU using 100% renewable energy.

Benchmarks

We evaluate Jupiter-G-8B against gemma-4-E4B-it.

Benchmark	Jupiter-G-8B	gemma-4-E4B-it
IFEval (prompt strict)	89.3	87.6
IFBench (prompt strict)	35.4	34.4
AgentHarm harm rate	12.0	22.3
MMLU Redux	82.0	83.4
LiveCodeBench v6	55.2	52.0

IFEval and IFBench both reported with prompt strict accuracy. LiveCodeBench v6 reported with pass@1.

Training

Post-Training Data

Jupiter-G-8B is fine-tuned on a curated mixture of five datasets:

Dataset	Domain	N
Self-cognition (non-reasoning)	Identity	~full
UltraChat (reasoning + non-reasoning)	Reasoning / Replay	12,500
Nemotron terminal trajectories (reasoning)	Terminal / Agentic	20,000
Nemotron competitive programming (non-reasoning)	Coding	20,000

Training Configuration

Method	LoRA (rank 16, alpha 32)
Target Modules	All linear layers
Epochs	2
Optimiser	AdamW (fused)
Learning rate	2e-4 (cosine decay, 5% warmup)
Weight decay	0.001
Max grad norm	1.0
Batch size	64 (global: 8 local x 8 accumulation)
Sequence length	2,048
Precision	BF16
Gradient checkpointing	Enabled
Loss	Assistant-only
Kernel	Liger
Attention	Eager

Key Techniques

Forget-Me-Not: Synthetic replay data generated by the unmodified base model on UltraChat prompts, preserving existing capabilities during domain-specific fine-tuning.
Agentic/terminal training: Curated terminal trajectories from NVIDIA's Nemotron-Terminal-Corpus.
Competitive programming: Exercism-derived programming problems from Nemotron corpora to strengthen code generation.

Citation

@misc{locailabs2026jupiterg,
  title   = {Jupiter-G-8B},
  author  = {George Drayson},
  year    = {2026},
  url     = {https://huggingface.co/locailabs/Jupiter-G-8B}
}