Instructions to use NoemaAI-labs/Noema-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NoemaAI-labs/Noema-2B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NoemaAI-labs/Noema-2B-GGUF",
	filename="Noema-2B-F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NoemaAI-labs/Noema-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NoemaAI-labs/Noema-2B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NoemaAI-labs/Noema-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NoemaAI-labs/Noema-2B-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": "NoemaAI-labs/Noema-2B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NoemaAI-labs/Noema-2B-GGUF:Q4_K_M

Ollama
How to use NoemaAI-labs/Noema-2B-GGUF with Ollama:
```
ollama run hf.co/NoemaAI-labs/Noema-2B-GGUF:Q4_K_M
```

Unsloth Studio

How to use NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NoemaAI-labs/Noema-2B-GGUF to start chatting

How to use NoemaAI-labs/Noema-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NoemaAI-labs/Noema-2B-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": "NoemaAI-labs/Noema-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NoemaAI-labs/Noema-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NoemaAI-labs/Noema-2B-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 NoemaAI-labs/Noema-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use NoemaAI-labs/Noema-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NoemaAI-labs/Noema-2B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "NoemaAI-labs/Noema-2B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use NoemaAI-labs/Noema-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/NoemaAI-labs/Noema-2B-GGUF:Q4_K_M
```

Lemonade

How to use NoemaAI-labs/Noema-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NoemaAI-labs/Noema-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Noema-2B-GGUF-Q4_K_M

List all available models

lemonade list

Noema-2B — GGUF

GGUF builds of NoemaAI-labs/Noema-2B, a ~2B reasoning model post-trained from Qwen/Qwen3.5-2B (hybrid Gated-DeltaNet architecture), for use with llama.cpp and compatible runtimes.

For the full model description, benchmarks, training recipe, and limitations, see the base model card.

⚠️ Requires Qwen3.5 (`qwen35`) architecture support in llama.cpp

This model uses the Qwen3.5 hybrid Gated-DeltaNet architecture. It will only load in a llama.cpp build that includes the qwen35 architecture (linear + full attention layers). On an older build you will get an "unknown architecture" / unsupported-arch error. Use a recent llama.cpp with Qwen3.5 support and build from source if your package manager's version is too old.

Files

File	Quant	Size	Notes
`Noema-2B-F16.gguf`	F16	3.5 GB	Full precision; conversion reference.
`Noema-2B-Q8_0.gguf`	Q8_0	1.9 GB	Near-lossless; highest-fidelity quant.
`Noema-2B-Q6_K.gguf`	Q6_K	1.5 GB	Very high quality, small quality loss.
`Noema-2B-Q4_K_M.gguf`	Q4_K_M	1.2 GB	Recommended quality/size balance.

All quants were produced from the same F16 conversion of the release weights and smoke-tested (load + generation) on each file.

Usage

Noema is tuned and evaluated in non-thinking mode, which is the default the embedded chat template applies. Pass --jinja so that template is used, and the model runs in its trained (non-thinking) regime automatically — no extra flags or prompt tags are needed.

Recommended sampling (the config Noema was evaluated under): --temp 0.7 --top-p 0.8 --top-k 20 --presence-penalty 1.5. Avoid --temp 0 / greedy decoding — this model family is documented to enter repetition loops under greedy sampling.

# One-shot, single-turn (non-thinking):
llama-cli -m Noema-2B-Q4_K_M.gguf --jinja -cnv -st \
  -p "A farmer has 17 red apples and 25 green apples. How many in total?" \
  -n 256 --temp 0.7 --top-p 0.8 --top-k 20 --presence-penalty 1.5

# Or run an OpenAI-compatible server (set the sampling params client-side,
# or pass the same flags here as server defaults):
llama-server -m Noema-2B-Q4_K_M.gguf --jinja -c 4096 \
  --temp 0.7 --top-p 0.8 --top-k 20 --presence-penalty 1.5

License

Apache-2.0, inherited from the Qwen/Qwen3.5-2B base model.

Downloads last month: 474

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Model tree for NoemaAI-labs/Noema-2B-GGUF

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

NoemaAI-labs/Noema-2B

Quantized

(3)

this model

Noema-2B — GGUF

⚠️ Requires Qwen3.5 (qwen35) architecture support in llama.cpp

Files

Usage

License

Model tree for NoemaAI-labs/Noema-2B-GGUF

⚠️ Requires Qwen3.5 (`qwen35`) architecture support in llama.cpp