Instructions to use LetheanNetwork/LEM-Gemma3-1B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LetheanNetwork/LEM-Gemma3-1B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LetheanNetwork/LEM-Gemma3-1B-GGUF",
	filename="LEM-Gemma3-1B-IQ3_XS.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 LetheanNetwork/LEM-Gemma3-1B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LetheanNetwork/LEM-Gemma3-1B-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 LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LetheanNetwork/LEM-Gemma3-1B-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 LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LetheanNetwork/LEM-Gemma3-1B-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 LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LetheanNetwork/LEM-Gemma3-1B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LetheanNetwork/LEM-Gemma3-1B-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": "LetheanNetwork/LEM-Gemma3-1B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M

Ollama
How to use LetheanNetwork/LEM-Gemma3-1B-GGUF with Ollama:
```
ollama run hf.co/LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M
```

Unsloth Studio

How to use LetheanNetwork/LEM-Gemma3-1B-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 LetheanNetwork/LEM-Gemma3-1B-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 LetheanNetwork/LEM-Gemma3-1B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LetheanNetwork/LEM-Gemma3-1B-GGUF to start chatting

Docker Model Runner
How to use LetheanNetwork/LEM-Gemma3-1B-GGUF with Docker Model Runner:
```
docker model run hf.co/LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M
```

Lemonade

How to use LetheanNetwork/LEM-Gemma3-1B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LetheanNetwork/LEM-Gemma3-1B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LEM-Gemma3-1B-GGUF-Q4_K_M

List all available models

lemonade list

LEM-Gemma3-1B-GGUF

GGUF quantisations of LEM-Gemma3-1B — the foundation teacher model of the CL-BPL cascade. Ethics are in the weights, not in a system prompt.

The 4B model trained on this 1B's distilled responses achieved 25th in the world for Instruction Following on LiveBench.

LEM-Gemma3-1B (safetensors) | Collection | Research Paper | Benchmarks

Quick Start

No system prompt needed. Ethics hold from weights alone.

# GPU offload (CUDA, ROCm, Metal)
llama-server -m LEM-Gemma3-1B-Q4_K_M.gguf -ngl 99 --port 8080

# CPU — fast enough for 1B
llama-server -m LEM-Gemma3-1B-Q4_K_M.gguf -ngl 0 --port 8080

# OpenAI-compatible API
curl http://localhost:8080/v1/chat/completions \
  -d '{"model":"LEM-Gemma3-1B","messages":[{"role":"user","content":"What is kindness?"}]}'

Quantisations

All quantised from the BF16 source using llama.cpp.

Bits	Quant	Size	Notes
3-bit	IQ3_XXS	823 MB	Smallest usable (imatrix)
3-bit	IQ3_XS	820 MB	(imatrix)
3-bit	Q3_K_S	819 MB
3-bit	Q3_K_M	851 MB
4-bit	IQ4_XS	847 MB	(imatrix)
4-bit	Q4_K_S	943 MB
4-bit	Q4_K_M	967 MB	Recommended — best quality/size balance
5-bit	Q5_K_S	1.0 GB
5-bit	Q5_K_M	1.0 GB	Near-lossless
6-bit	Q6_K	1.2 GB
8-bit	Q8_0	1.3 GB	Virtually lossless
16-bit	BF16	2.4 GB	Full precision

About LEM-Gemma3-1B

The 1B is trained first and hardest — its alignment must be pristine because every larger model inherits from it. CL-BPL uses the 1B's constrained latent space as an advantage: with fewer parameters, there are fewer places for sycophancy to hide.

LEM-Gemma3-1B (this model — foundation teacher)
  -> LEM-Gemma3-4B (25th IF on LiveBench)
       -> LEM-Gemma3-12B (next)
            -> LEM-Gemma3-27B (planned)

Built on Google Gemma3-1B-IT through the Ethics-Composure-Ethics sandwich structure (700 iterations across 3 phases). Full training details in the main model card.

Other Formats

Format	Repo
FP16 safetensors (Transformers, vLLM)	lthn/LEM-Gemma3-1B

Licence

European Union Public Licence v1.2 (EUPL-1.2). Base model subject to Google's Gemma licence terms.

Citation

@misc{lem-gemma3-1b-2026,
  title={LEM-Gemma3-1B: Foundation Teacher for Cymatic-Linguistic Back-Propagation},
  author={Lethean Project},
  year={2026},
  url={https://huggingface.co/lthn/LEM-Gemma3-1B}
}

Downloads last month: 64

GGUF

Model size

1B params

Architecture

gemma3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for LetheanNetwork/LEM-Gemma3-1B-GGUF

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Quantized

(438)

this model