Instructions to use nativemind/sphere_047_m4_overnight-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nativemind/sphere_047_m4_overnight-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nativemind/sphere_047_m4_overnight-gguf",
	filename="sphere_047_m4_overnight-q4_0.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 nativemind/sphere_047_m4_overnight-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nativemind/sphere_047_m4_overnight-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nativemind/sphere_047_m4_overnight-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 nativemind/sphere_047_m4_overnight-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nativemind/sphere_047_m4_overnight-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 nativemind/sphere_047_m4_overnight-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nativemind/sphere_047_m4_overnight-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 nativemind/sphere_047_m4_overnight-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nativemind/sphere_047_m4_overnight-gguf:Q4_K_M

Use Docker

docker model run hf.co/nativemind/sphere_047_m4_overnight-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use nativemind/sphere_047_m4_overnight-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nativemind/sphere_047_m4_overnight-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": "nativemind/sphere_047_m4_overnight-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nativemind/sphere_047_m4_overnight-gguf:Q4_K_M

Ollama
How to use nativemind/sphere_047_m4_overnight-gguf with Ollama:
```
ollama run hf.co/nativemind/sphere_047_m4_overnight-gguf:Q4_K_M
```

Unsloth Studio new

How to use nativemind/sphere_047_m4_overnight-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 nativemind/sphere_047_m4_overnight-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 nativemind/sphere_047_m4_overnight-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nativemind/sphere_047_m4_overnight-gguf to start chatting

Docker Model Runner
How to use nativemind/sphere_047_m4_overnight-gguf with Docker Model Runner:
```
docker model run hf.co/nativemind/sphere_047_m4_overnight-gguf:Q4_K_M
```

Lemonade

How to use nativemind/sphere_047_m4_overnight-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nativemind/sphere_047_m4_overnight-gguf:Q4_K_M

Run and chat with the model

lemonade run user.sphere_047_m4_overnight-gguf-Q4_K_M

List all available models

lemonade list

СЛЕДОВАТЕЛЬ - Сфера 047 (M4 Overnight) - GGUF

Это квантизованная версия модели nativemind/sphere_047_m4_overnight в формате GGUF, оптимизированная для запуска на устройствах с ограниченными ресурсами.

📋 О модели

Базовая модель: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Обучено на: M4 MacBook Pro за ~2 часа
Метод: LoRA (rank=8)
Датасет: Реальное уголовное дело + Alpaca + Kene
Формат: GGUF (конвертировано из PyTorch + LoRA)

📦 Доступные квантизации

Файл	Квантизация	Размер	Описание
`sphere_047_m4_overnight.gguf`	F16	~2.2 GB	Полная точность
`sphere_047_m4_overnight-q4_0.gguf`	Q4_0	~630 MB	4-bit квантизация
`sphere_047_m4_overnight-q4_k_m.gguf`	Q4_K_M	~650 MB	4-bit K-квантизация (средняя)
`sphere_047_m4_overnight-q5_k_m.gguf`	Q5_K_M	~750 MB	5-bit K-квантизация (средняя)
`sphere_047_m4_overnight-q8_0.gguf`	Q8_0	~1.2 GB	8-bit квантизация

🚀 Использование

llama.cpp

# Загрузите модель
huggingface-cli download nativemind/sphere_047_m4_overnight-gguf sphere_047_m4_overnight-q4_k_m.gguf

# Запустите inference
./llama.cpp/build/bin/llama-cli -m sphere_047_m4_overnight-q4_k_m.gguf -p "Проанализируй документ..." -n 512

Flutter Llama Plugin

import 'package:flutter_llama/flutter_llama.dart';

final llama = FlutterLlama();

// Загрузите модель
await llama.loadModel(
  modelPath: 'path/to/sphere_047_m4_overnight-q4_k_m.gguf',
  config: LlamaConfig(
    contextSize: 2048,
    numThreads: 4,
  ),
);

// Генерируйте текст
final response = await llama.generateText(
  prompt: 'Проанализируй документ: ...',
  maxTokens: 512,
);

print(response);

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="sphere_047_m4_overnight-q4_k_m.gguf",
    n_ctx=2048,
    n_threads=4,
)

output = llm(
    "Проанализируй документ: ...",
    max_tokens=512,
    temperature=0.7,
)

print(output['choices'][0]['text'])

📱 Рекомендации по устройствам

Мобильные устройства (iOS/Android): Q4_0 или Q4_K_M
Ноутбуки/Desktop: Q5_K_M или Q8_0
Серверы: F16 (полная точность)

🎯 Примеры промптов

Проанализируй следующий документ и выдели ключевые факты...

Составь краткое резюме материалов дела...

Определи противоречия в показаниях свидетелей...

⚖️ Лицензия

Apache 2.0

🙏 Благодарности

Базовая модель: TinyLlama Team
GGUF конвертация: llama.cpp

⚖️ Истина восторжествует! 🕉️

Downloads last month: 45

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

8-bit

View +1 variant

Model tree for nativemind/sphere_047_m4_overnight-gguf

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Quantized

(145)

this model

Collection including nativemind/sphere_047_m4_overnight-gguf

braindler_spheres

Collection

5 items • Updated Oct 26, 2025 • 1