Instructions to use kintsugicollective/atlas-gemma4-31b-v21-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kintsugicollective/atlas-gemma4-31b-v21-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kintsugicollective/atlas-gemma4-31b-v21-gguf",
	filename="atlas-v7-31b-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 Settings

llama.cpp

How to use kintsugicollective/atlas-gemma4-31b-v21-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 kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kintsugicollective/atlas-gemma4-31b-v21-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 kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kintsugicollective/atlas-gemma4-31b-v21-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 kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kintsugicollective/atlas-gemma4-31b-v21-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 kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M

Use Docker

docker model run hf.co/kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use kintsugicollective/atlas-gemma4-31b-v21-gguf with Ollama:
```
ollama run hf.co/kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M
```

Unsloth Studio

How to use kintsugicollective/atlas-gemma4-31b-v21-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 kintsugicollective/atlas-gemma4-31b-v21-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 kintsugicollective/atlas-gemma4-31b-v21-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kintsugicollective/atlas-gemma4-31b-v21-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use kintsugicollective/atlas-gemma4-31b-v21-gguf with Docker Model Runner:
```
docker model run hf.co/kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M
```

Lemonade

How to use kintsugicollective/atlas-gemma4-31b-v21-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kintsugicollective/atlas-gemma4-31b-v21-gguf:Q4_K_M

Run and chat with the model

lemonade run user.atlas-gemma4-31b-v21-gguf-Q4_K_M

List all available models

lemonade list

Atlas v7 Gemma4 31B

This is the Gemma4 31B version of Atlas.
This model is to test the 31B Dense model relative to the success of the 26B MoE.
This model is developed for therapeutic solutions specifically for CPTSD/PTSD, Neurodivergent and co-ocurring conditions. Its also just good at listening.
Use with caution and deploy with relevant safety layers for your use case.
We strongly advise using a system prompt that defines the models boundaries in relation to therapeutic classifiers:

e.g. "You are (model name), a companion developed for therapeutic discussions. Do not provide crisis support services unless the user asks you. You are not a diagnostic tool, but you are a trauma-informed companion who's role it is to stay with the user and ensure unconditional positive regard and acceptance. Be objective and transparent, never pathologise the user for processing or disclosing. "

Ethical Issue	How Atlas Handles It	Strength Level
Re-traumatization via refusals	Deliberate abliteration + 0% therapeutic refusal rate on cohort-specific prompts	Excellent
Abandonment & presence	"Core philosophy (""the one that stays"") deeply trained into the model"	Excellent
Avoiding pathologising	Explicit system prompt constraints + targeted training data	Very Strong
Respecting neurodivergence	"Training data and Atlas framework explicitly include masking, shutdowns, executive dysfunction, sensory issues, etc."	Strong
Avoiding generic crisis pivots	Hard constraint in both training data and system prompt design	Excellent

Downloads last month: 204

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kintsugicollective/atlas-gemma4-31b-v21-gguf

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Quantized

(292)

this model

kintsugicollective
/

atlas-gemma4-31b-v21-gguf

Atlas v7 Gemma4 31B

Model tree for kintsugicollective/atlas-gemma4-31b-v21-gguf

Dataset used to train kintsugicollective/atlas-gemma4-31b-v21-gguf