Hugging Face's logo

kintsugicollective
/
atlas-gemma4-31b-v21-gguf

GGUF
Unsloth
Atlas
CPTSD
PTSD
conversational
Model card Files
xet
 Community
How to use from
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
Quick Links

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
46
GGUF
Model size
31B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware

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
(342)
this model

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