Instructions to use NeveAI/Neve-Echo-S-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeveAI/Neve-Echo-S-4B-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="NeveAI/Neve-Echo-S-4B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NeveAI/Neve-Echo-S-4B-GGUF", dtype="auto")

llama-cpp-python

How to use NeveAI/Neve-Echo-S-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NeveAI/Neve-Echo-S-4B-GGUF",
	filename="Neve-Echo-S-4B-Q8_K_XL.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use NeveAI/Neve-Echo-S-4B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL
# Run inference directly in the terminal:
llama-cli -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL
# Run inference directly in the terminal:
llama-cli -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

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 NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL
# Run inference directly in the terminal:
./llama-cli -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

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 NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

Use Docker

docker model run hf.co/NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

LM Studio
Jan

vLLM

How to use NeveAI/Neve-Echo-S-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeveAI/Neve-Echo-S-4B-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": "NeveAI/Neve-Echo-S-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

SGLang

How to use NeveAI/Neve-Echo-S-4B-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 "NeveAI/Neve-Echo-S-4B-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": "NeveAI/Neve-Echo-S-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "NeveAI/Neve-Echo-S-4B-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": "NeveAI/Neve-Echo-S-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use NeveAI/Neve-Echo-S-4B-GGUF with Ollama:
```
ollama run hf.co/NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL
```

Unsloth Studio new

How to use NeveAI/Neve-Echo-S-4B-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 NeveAI/Neve-Echo-S-4B-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 NeveAI/Neve-Echo-S-4B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NeveAI/Neve-Echo-S-4B-GGUF to start chatting

Pi new

How to use NeveAI/Neve-Echo-S-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

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": "Neve-Echo-S-4B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NeveAI/Neve-Echo-S-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL
```

Lemonade

How to use NeveAI/Neve-Echo-S-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NeveAI/Neve-Echo-S-4B-GGUF:Q8_K_XL

Run and chat with the model

lemonade run user.Neve-Echo-S-4B-GGUF-Q8_K_XL

List all available models

lemonade list

Neve-Echo-S-4B-GGUF

## Introdução

O Neve Echo S é um modelo de linguagem de última geração focado em uso geral e raciocínio para tarefas rápidas. Esta versão em formato GGUF foi otimizada pela NeveAI para oferecer o equilíbrio ideal entre precisão lógica e eficiência computacional.

Destaques do Modelo

Este modelo foi desenvolvido para uso geral e execução de tarefas diversas, focando em:

Raciocínio Avançado (Thinking): Projetado como um modelo altamente capaz de raciocínio, com suporte a modos de pensamento estruturado para tarefas complexas.
Uso Geral e Produtividade: Otimizado para uma ampla variedade de tarefas como geração de texto, assistência, explicações, planejamento e automação.
Multimodalidade (Texto + Imagem): Capaz de processar entradas multimodais com suporte a diferentes resoluções e proporções.
Tool Calling e System Prompt: Suporte nativo a chamadas de função e ao papel system, permitindo maior controle e integração com ferramentas externas.

Benchmark de Performance

O Neve Echo 4 demonstra desempenho alinhado a modelos de ponta em múltiplas categorias:

Categoria	Benchmark	Gemma 4 31B	Gemma 4 26B A4B	Neve Echo S
Knowledge	MMLU Pro	85.2%	82.6%	69.4%
Reasoning	GPQA Diamond	84.3%	82.3%	58.6%
Math	AIME 2026	89.2%	88.3%	42.5%
General	BigBench Extra Hard	74.4%	64.8%	33.1%

Detalhes da Arquitetura

Arquitetura: Mixture of Experts (MoE) com atenção híbrida (local + global intercalado).
Parâmetros: ~4B totais (com subset ativo por token para eficiência).
Janela de Contexto: Até 256K tokens.
Camadas: Arquitetura profunda com atenção global na camada final.
MoE: Roteamento dinâmico de experts (subset ativo por inferência), otimizando performance e uso de memória.

Como utilizar (GGUF)

Este modelo é compatível com llama.cpp, Ollama, LM Studio e outras ferramentas que suportam o formato GGUF. Foco direcionado ao uso do modelo na plataforma autoral da organização NeveAI

Licença

Este repositório e os pesos do modelo estão licenciados sob a Licença Apache 2.0.

Contato

Se tiver qualquer dúvida, por favor, levante um issue ou entre em contato conosco em NeveIA.

Downloads last month: 309

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

8-bit

Model tree for NeveAI/Neve-Echo-S-4B-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(161)

this model

Collection including NeveAI/Neve-Echo-S-4B-GGUF

Neve Echo

Collection

Modelos de uso geral e raciocínio para tarefas rápidas e variadas. • 2 items • Updated 9 days ago