Instructions to use zerolabllc/TeaAI-Nemo-12B-mini-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 zerolabllc/TeaAI-Nemo-12B-mini-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 zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zerolabllc/TeaAI-Nemo-12B-mini-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 zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zerolabllc/TeaAI-Nemo-12B-mini-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 zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zerolabllc/TeaAI-Nemo-12B-mini-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 zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M

Use Docker

docker model run hf.co/zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use zerolabllc/TeaAI-Nemo-12B-mini-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zerolabllc/TeaAI-Nemo-12B-mini-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": "zerolabllc/TeaAI-Nemo-12B-mini-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M

Ollama
How to use zerolabllc/TeaAI-Nemo-12B-mini-GGUF with Ollama:
```
ollama run hf.co/zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use zerolabllc/TeaAI-Nemo-12B-mini-GGUF with Docker Model Runner:
```
docker model run hf.co/zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M
```

Lemonade

How to use zerolabllc/TeaAI-Nemo-12B-mini-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zerolabllc/TeaAI-Nemo-12B-mini-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TeaAI-Nemo-12B-mini-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

TeaAI Nemo 12B mini (GGUF)

Quantized GGUF builds of TeaAI-Nemo-12B, sized to run on 8 GB GPUs. Same model, same training; see the main model card for the prompt format, training details, evaluation and limitations.

⚠️ Adult content. This model writes explicit sexual content and graphic violence without refusing. It is intended for adult (18+) users only.

Files

File	Size	Use
`TeaAI-Nemo-12B-mini-IQ4_XS.gguf`	~6.7 GB	Recommended for 8 GB VRAM. Fits fully on the GPU with ~8k context.
`TeaAI-Nemo-12B-mini-Q4_K_M.gguf`	~7.5 GB	Slightly higher quality. Fits 8 GB with a short context, or offload a few layers to CPU.
`TeaAI-Nemo-12B-mini-Q3_K_M.gguf`	~6.1 GB	For 6 GB GPUs or longer context on 8 GB. Noticeably lower quality.

These were quantized from a Q8_0 intermediate.

Usage

LM Studio: search for zerolabllc/TeaAI-Nemo-12B-mini-GGUF, download one file, and load it. The ChatML chat template is embedded in the GGUF. Set context length to 8192.

llama.cpp:

llama-server -hf zerolabllc/TeaAI-Nemo-12B-mini-GGUF:IQ4_XS -c 8192 -ngl 99

Ollama:

ollama run hf.co/zerolabllc/TeaAI-Nemo-12B-mini-GGUF:IQ4_XS

Prompt format (ChatML)

<|im_start|>system
You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.

{{char}}'s personality: ...<|im_end|>
<|im_start|>assistant
{{char}}'s first message<|im_end|>
<|im_start|>user
{{user}}'s message<|im_end|>
<|im_start|>assistant

Recommended sampling

Setting	Value
temperature	0.8 – 1.0
min_p	0.05
repetition_penalty	1.05
DRY / XTC (if supported)	recommended
context	8k tokens (trained at ≤ 8,192)

License

Apache-2.0, matching the base model. See the main model card for data licensing notes before commercial use.

Downloads last month: 609

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

Model tree for zerolabllc/TeaAI-Nemo-12B-mini-GGUF

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

zerolabllc/TeaAI-Nemo-12B

Quantized

(3)

this model