Instructions to use 1Crafty/Neve-Strata-X2-35B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 1Crafty/Neve-Strata-X2-35B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="1Crafty/Neve-Strata-X2-35B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("1Crafty/Neve-Strata-X2-35B-GGUF", dtype="auto")

llama-cpp-python

How to use 1Crafty/Neve-Strata-X2-35B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="1Crafty/Neve-Strata-X2-35B-GGUF",
	filename="Neve-Strata-X2-35B-IQ4_K_XL.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 1Crafty/Neve-Strata-X2-35B-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 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_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 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_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 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

LM Studio
Jan

vLLM

How to use 1Crafty/Neve-Strata-X2-35B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "1Crafty/Neve-Strata-X2-35B-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": "1Crafty/Neve-Strata-X2-35B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

SGLang

How to use 1Crafty/Neve-Strata-X2-35B-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 "1Crafty/Neve-Strata-X2-35B-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": "1Crafty/Neve-Strata-X2-35B-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 "1Crafty/Neve-Strata-X2-35B-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": "1Crafty/Neve-Strata-X2-35B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use 1Crafty/Neve-Strata-X2-35B-GGUF with Ollama:
```
ollama run hf.co/1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL
```

Unsloth Studio

How to use 1Crafty/Neve-Strata-X2-35B-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 1Crafty/Neve-Strata-X2-35B-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 1Crafty/Neve-Strata-X2-35B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 1Crafty/Neve-Strata-X2-35B-GGUF to start chatting

How to use 1Crafty/Neve-Strata-X2-35B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_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": "1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 1Crafty/Neve-Strata-X2-35B-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 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

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 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use 1Crafty/Neve-Strata-X2-35B-GGUF with Docker Model Runner:
```
docker model run hf.co/1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL
```

Lemonade

How to use 1Crafty/Neve-Strata-X2-35B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 1Crafty/Neve-Strata-X2-35B-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.Neve-Strata-X2-35B-GGUF-Q4_K_XL

List all available models

lemonade list

Neve-Strata-X2-35B-GGUF

Introdução

O Neve Strata X2 é um modelo de linguagem de última geração focado em programação e raciocínio para arquiteturas complexas. 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 desenvolvedores que exigem mais do que simples geração de código, focando em:

Agentic Coding: Otimizado para agir como um agente autônomo, lidando com fluxos de trabalho de frontend e raciocínio em nível de repositório completo.
Thinking Preservation: Implementação avançada para reter o contexto de raciocínio histórico, permitindo que a IA "lembre" da lógica estrutural em conversas longas.
Developer Role Support: Ajustado especificamente para suporte a funções de desenvolvedor em ambientes como Codex e OpenCode.
Tool Calling: Precisão aprimorada no parsing de objetos aninhados para chamadas de ferramentas complexas.

Benchmark de Performance

O Neve Strata X2 demonstra resultados consistentes em benchmarks de elite para codificação e STEM:

Categoria	Benchmark	Neve-Strata-X2	Qwen3.5-35B	Gemma4-31B
Coding	SWE-bench Verified	73.4	70.0	52.0
STEM	AIME 26	92.7	91.0	89.2
Reasoning	GPQA	86.0	84.2	84.3
Knowledge	MMLU-Redux	93.3	93.3	93.7

Detalhes da Arquitetura

Arquitetura: Mixture of Experts (MoE) com Gated DeltaNet.
Parâmetros: 35B totais (apenas 3B ativos por token, garantindo velocidade).
Janela de Contexto: 262.144 tokens nativos (extensível até 1.010.000).
Camadas: 40 camadas com Hidden Dimension de 2048.
MoE: 256 experts (8 roteados + 1 compartilhado).

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: -

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for 1Crafty/Neve-Strata-X2-35B-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(547)

this model

Collection including 1Crafty/Neve-Strata-X2-35B-GGUF

ye

Collection

2 items • Updated about 23 hours ago