Instructions to use lxcorp/Link-270M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lxcorp/Link-270M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="lxcorp/Link-270M-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lxcorp/Link-270M-GGUF", dtype="auto")

llama-cpp-python

How to use lxcorp/Link-270M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lxcorp/Link-270M-GGUF",
	filename="link1-270m-iq4_nl-imat.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use lxcorp/Link-270M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lxcorp/Link-270M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lxcorp/Link-270M-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 lxcorp/Link-270M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lxcorp/Link-270M-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 lxcorp/Link-270M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lxcorp/Link-270M-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 lxcorp/Link-270M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lxcorp/Link-270M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lxcorp/Link-270M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lxcorp/Link-270M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lxcorp/Link-270M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lxcorp/Link-270M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lxcorp/Link-270M-GGUF:Q4_K_M

SGLang

How to use lxcorp/Link-270M-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 "lxcorp/Link-270M-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lxcorp/Link-270M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "lxcorp/Link-270M-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lxcorp/Link-270M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use lxcorp/Link-270M-GGUF with Ollama:
```
ollama run hf.co/lxcorp/Link-270M-GGUF:Q4_K_M
```

Unsloth Studio new

How to use lxcorp/Link-270M-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 lxcorp/Link-270M-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 lxcorp/Link-270M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lxcorp/Link-270M-GGUF to start chatting

Docker Model Runner
How to use lxcorp/Link-270M-GGUF with Docker Model Runner:
```
docker model run hf.co/lxcorp/Link-270M-GGUF:Q4_K_M
```

Lemonade

How to use lxcorp/Link-270M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lxcorp/Link-270M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Link-270M-GGUF-Q4_K_M

List all available models

lemonade list

🔗 Link-270M-GGUF

Link-270M é um modelo de linguagem leve e eficiente, desenvolvido pela LambdaXi Corp, ideal para execução local, dispositivos com poucos recursos e pipelines baseados em GGUF.

Este repositório funciona como um hub único contendo todas as quantizações oficiais do modelo Link-270M, prontas para uso imediato.

📦 Modelos Disponíveis

Quantização	Bits	Arquivo
IQ4_NL	4-bit	`link1-270m-iq4_nl.gguf`
Q4_K_M	4-bit	`link1-270m-q4_k_m.gguf`
Q8_0	8-bit	`link1-270m-q8_0.gguf`

📌 Todos os arquivos seguem o padrão GGUF oficial e são compatíveis com llama.cpp.

🧠 Sobre o Modelo

Nome: Link-270M
Parâmetros: ~270 milhões
Arquitetura: Causal Language Model
Contexto máximo: 32K tokens
Foco: velocidade, eficiência e execução local
Formato: GGUF

Projetado para ser rápido, direto e altamente utilizável em ambientes restritos.

🚀 Como Usar

llama.cpp (CLI)

llama -m link1-270m-q4_k_m.gguf -p "Olá, quem é você?"

LM Studio

Abra o LM Studio
Importe o arquivo .gguf
Selecione o modelo
Gere texto normalmente

text-generation-webui

Coloque o .gguf na pasta de modelos
Inicie o webui
Selecione Link-270M

⚙️ Configurações Recomendadas

Parâmetro	Valor
temperature	0.7 – 1.0
top_k	40 – 64
top_p	0.85 – 0.95
repeat_penalty	1.1

Ajuste conforme o caso de uso (chat, código, texto criativo).

⚠️ Limitações Conhecidas

Modelo pequeno → menor profundidade que LLMs grandes
Pode alucinar em tarefas altamente técnicas
Melhor desempenho com prompts claros e objetivos

🧩 Compatibilidade

✔ llama.cpp
✔ LM Studio
✔ text-generation-webui
✔ KoboldCPP
✔ Qualquer runtime compatível com GGUF

🏷️ Identidade do Modelo

Nome: Link
Criador: LambdaXi Corp
Responsável: Marius Jabami

Link é um modelo independente, projetado para execução local e uso livre.

📚 Citação

@misc{link270m_2026,
  title={Link 270M GGUF},
  author={LambdaXi Corp},
  year={2026},
  howpublished={Hugging Face},
  note={https://huggingface.co/lxcorp/Link-270M-GGUF}
}

❤️ Agradecimentos

Obrigado por usar Link-270M-GGUF.
Este repositório existe para centralizar todas as quantizações oficiais em um único lugar.

Desenvolvido com foco em liberdade, eficiência e execução local.

Downloads last month: 12

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

4-bit

8-bit

lxcorp
/

Link-270M-GGUF