Instructions to use tmancino/te-nims-e4b-stage9-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tmancino/te-nims-e4b-stage9-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tmancino/te-nims-e4b-stage9-gguf",
	filename="nims-e4b-stage9-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tmancino/te-nims-e4b-stage9-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tmancino/te-nims-e4b-stage9-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tmancino/te-nims-e4b-stage9-gguf:Q4_K_M

Use Docker

docker model run hf.co/tmancino/te-nims-e4b-stage9-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use tmancino/te-nims-e4b-stage9-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tmancino/te-nims-e4b-stage9-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tmancino/te-nims-e4b-stage9-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tmancino/te-nims-e4b-stage9-gguf:Q4_K_M

Ollama
How to use tmancino/te-nims-e4b-stage9-gguf with Ollama:
```
ollama run hf.co/tmancino/te-nims-e4b-stage9-gguf:Q4_K_M
```

Unsloth Studio new

How to use tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tmancino/te-nims-e4b-stage9-gguf to start chatting

Pi new

How to use tmancino/te-nims-e4b-stage9-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tmancino/te-nims-e4b-stage9-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": "tmancino/te-nims-e4b-stage9-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-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 tmancino/te-nims-e4b-stage9-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use tmancino/te-nims-e4b-stage9-gguf with Docker Model Runner:
```
docker model run hf.co/tmancino/te-nims-e4b-stage9-gguf:Q4_K_M
```

Lemonade

How to use tmancino/te-nims-e4b-stage9-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tmancino/te-nims-e4b-stage9-gguf:Q4_K_M

Run and chat with the model

lemonade run user.te-nims-e4b-stage9-gguf-Q4_K_M

List all available models

lemonade list

TE-NIMS E4B Stage 9 — Q4_K_M GGUF

Fine-tuned Gemma 4 E4B for NIMS / ICS decision support in civilian emergency management. Trained through 9 warm-start SFT stages on curated FEMA doctrine, ICS forms, and after-action reports.

Base: google/gemma-4-e4b-it (dense 4B edge model)
Adapter lineage: tmancino/te-nims-e4b-stage9
Quantization: Q4_K_M (~5GB, runs on 8GB VRAM)
Training: 9-stage warm-start SFT chain (Stage 9 is the production checkpoint)
ODA eval score: 0.916 on the 52-case TE NIMS Bench

This repository is the deployable text inference artifact. It is the model downloaded by the TE NIMS demo on first boot and wrapped by Ollama as the local runtime severian-ollama.

Use cases

Incident Commander decision support
ICS-201 / ICS-202 / ICS-213 form generation
NIMS doctrine grounding for first-responder questions
Unified Command planning and mass-casualty triage

Quickstart

Ollama

ollama run hf.co/tmancino/te-nims-e4b-stage9-gguf

Docker (full FOB demo UI)

git clone https://github.com/TerminusEstAI/te-nims-demo
cd te-nims-demo && docker compose up
open http://localhost:8765

llama.cpp

huggingface-cli download tmancino/te-nims-e4b-stage9-gguf nims-e4b-stage9-q4_k_m.gguf
./llama-server -m nims-e4b-stage9-q4_k_m.gguf -c 8192

Live demo

Full Incident Commander UI: https://demo.terminusest.ai

Source: https://github.com/TerminusEstAI/te-nims-demo

Deployment notes

Demo runtime name: severian-ollama
Intended runtime: Ollama or llama.cpp-compatible GGUF serving
The demo's multimodal severian-vision sidecar is a separate deployment path with separate vision artifacts

Citation

Built by Terminus Est AI for the Kaggle Gemma 4 Good Hackathon, May 2026.

License

CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/

Base model google/gemma-4-e4b-it retains its original Apache 2.0 license and Gemma Terms of Use.

Downloads last month: 218

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

4-bit