Instructions to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF")
model = AutoModelForCausalLM.from_pretrained("NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF")

llama-cpp-python

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF",
	filename="LFM2.5-1.2B-Instruct.Q2_K.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 NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NovachronoAI/Nova-LFM-1.2B-Thinking-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": "NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M

SGLang

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with Ollama:
```
ollama run hf.co/NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M
```

Unsloth Studio new

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF to start chatting

Pi new

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NovachronoAI/Nova-LFM-1.2B-Thinking-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": "NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-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 NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with Docker Model Runner:
```
docker model run hf.co/NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M
```

Lemonade

How to use NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nova-LFM-1.2B-Thinking-GGUF-Q4_K_M

List all available models

lemonade list

🧠 Nova-LFM 1.2B Thinking

System 2 Reasoning at the Edge

📥 Download Full Model | 📜 Technical Report (Coming Soon)

📖 Overview

Nova-LFM 1.2B is a state-of-the-art "Thinking" model engineered for efficiency. It brings reasoning capabilities—typically reserved for 7B+ models—down to the 1.2B parameter class, making it possible to run complex logic chains on edge devices like Raspberry Pis, older smartphones, and laptops.

Built on the Liquid LFM-2.5 architecture, this model utilizes a novel Hybrid Self-Correction fine-tuning method. It pauses to "think" (denoted by <think> tags), verifies its own logic, and corrects errors before generating a final answer.

🌟 Key Capabilities

System 2 Thinking: Breaks down multi-step math and logic problems instead of guessing.
Edge-Native: Runs on <3GB VRAM (FP16) or <1GB (Quantized).
Balanced Profile: engineered to excel at Math (GSM8K) without sacrificing General Knowledge (MMLU).

📊 Benchmark Performance

Nova-LFM outperforms the industry standard (Llama 3.2 1B) and larger models (Gemma 2 2B) in mathematical reasoning, while maintaining a higher general knowledge score than specialized "math-only" models.

Model	Parameters	Math Reasoning (GSM8K)	Knowledge (MMLU)	Verdict
Nova-LFM (Ours)	1.2B	53.5% 🚀	50.1%	Best Balance
Llama 3.2 Instruct	1.0B	44.4%	42.9%	Baseline
Gemma 2	2.6B	46.4%	51.7%	Inefficient
DeepSeek R1 Distill	1.5B	69.9%	39.2% 🔻	Knowledge Collapse
SmolLM2	1.7B	31.1%	48.9%	Weak Reasoning

Note: Scores represent 5-shot evaluations using EleutherAI LM Harness. DeepSeek R1 shows significant degradation in general knowledge (MMLU < 40%) despite high math scores. Nova-LFM maintains >50% MMLU for general-purpose usability.

🚀 Quick Start

Option 1: Python (Transformers)

Requires transformers >= 4.46.0

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "NovachronoAI/Nova-LFM-1.2B-Thinking"

# Load the model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    device_map="auto"
)

# Define the prompt
prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
If I have 3 apples and eat one, then buy two more, how many do I have?

### Response:
"""

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Generate with reasoning (Temperature 0.6 recommended)
outputs = model.generate(
    **inputs, 
    max_new_tokens=512, 
    temperature=0.6, 
    do_sample=True
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Option 2: Ollama (Local)

For the fastest inference on CPU/Mac/Edge: ollama run hf.co/NovachronoAI/Nova-LFM-1.2B-Thinking-GGUF

🔬 Methodology: Hybrid Self-Correction

Standard small models often hallucinate because they rush to predict the next token. Nova-LFM was trained to pause and verify.

Dataset Construction: We curated a hybrid dataset combining:
- 11k Standard CoT: High-quality linear reasoning chains (Step A → Step B).
- 4k Self-Correction Traces: Synthetic data where the model explicitly doubts itself (e.g., "Wait, that calculation seems off..."), catches the error, and corrects it.
Fine-Tuning: Trained using Unsloth with LoRA adapters targeting the unique Liquid Neural Network layers (in_proj, out_proj, w1-w3). This dual approach teaches the model that backtracking is allowed, significantly reducing logic errors in multi-step tasks.

⚠️ Limitations

Hallucination: As a 1.2B model, it does not possess the vast world knowledge of a 70B model. It may hallucinate obscure facts or dates.
Token Artifacts: Rarely, raw training tags like [Reasoning] may appear in the output.
Context: Optimized for short-to-medium reasoning tasks (up to 8k context).

📜 Citation

If you use this model in your research or application, please cite:

@misc{nova-lfm-2026,
    title = {Nova-LFM: Scalable System 2 Reasoning at the 1B Scale},
    author = {Novachrono},
    year = {2026},
    publisher = {HuggingFace},
    url = {[https://huggingface.co/NovachronoAI/Nova-LFM-1.2B-Thinking](https://huggingface.co/NovachronoAI/Nova-LFM-1.2B-Thinking)}
}

Built with ❤️ by NovachronoAI using Unsloth & Liquid AI

Downloads last month: 134

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

NovachronoAI
/

Nova-LFM-1.2B-Thinking-GGUF