Instructions to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-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 iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

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 iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

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 iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Use Docker

docker model run hf.co/iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iBotIA/Qwen3.8-4B-Empero-AI-FullStack-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": "iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Ollama
How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with Ollama:
```
ollama run hf.co/iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K
```
Unsloth Desktop

How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with Docker Model Runner:
```
docker model run hf.co/iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K
```

Lemonade

How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Run and chat with the model

lemonade run user.Qwen3.8-4B-Empero-AI-FullStack-GGUF-Q6_K

List all available models

lemonade list

Hermes Agent

How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-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 iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

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 iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.8-4B-Empero-AI-Distill-FullStack — GGUF

Model Overview

This repository contains the optimized GGUF quantization of Qwen3.8-4B-Empero-AI-Distill-FullStack, fine-tuned using the Unsloth framework for advanced full-stack web and mobile software development pipelines.

The base architecture features a full-parameter distillation of reasoning traces (Chain-of-Thought via <think>...</think> tags) from the frontier-scale Qwen3.8 2.4T A95B teacher model developed by Empero-AI. This configuration offers advanced local planning, logic, and code compilation compliance within a highly efficient 4-billion parameter footprint.

🔗 Repository Links

Safetensors Version (9.3GB Heavy Build): https://huggingface.co/iBotIA/Qwen3.8-4B-Empero-AI-FullStack
GGUF Version (3.5GB Optimized Quantization): https://huggingface.co/iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF

📚 Injected Knowledge Stack (Fine-Tuning Data)

The model underwent continuous pre-training on 279,049 curated data segments across 8 strictly isolated developer knowledge directories:

Mobile / Cross-Platform: Flutter (Modern structural widgets and lifecycle state management).
Full-Stack Web Architecture: React Router v8 (Framework Mode via Vite, server-loaders, and async server-actions routing).
Backend & Runtime Engine: NestJS & Node.js (API architecture, scalable middleware, and server streams).
Database & Persistence Layers: Prisma ORM & Drizzle ORM (Schema modeling, relational builders, and safe SQL migrations).
Language & System Rigor: TypeScript (Strict typing patterns to enforce self-debugging and runtime stability).
Design & UI Systems: Tailwind CSS & Shadcn UI / Radix Primitives (Utility class layout embedded in JSX/TSX components).

📊 Training Logs & Learning Curve

The fine-tuning process completed 250 hardware-optimized steps on a T4 GPU. The learning curve showed a definitive late convergence ("Eureka" moment) near step 140, where the weights successfully aligned cross-stack framework logic.

Step 10 (Start): Loss = 10.427407
Step 50: Loss = 8.580708
Step 140 (Logical drop): Loss = 7.571871
Step 250 (Final score): Loss = 8.050256

📦 Quantization Specifications

File: Qwen3.8-4B-Empero-AI-Distill-FullStack-Q6_K.gguf
Format: Q6_K (6-bit quantization)
Size: ~3.56 GB
Quality: Near-lossless precision compared to the 16-bit reference build.

Note: The llama.cpp converter intentionally skipped the multimodal vision projector weights (KeyError: image_mean) during compilation. This streamlines the GGUF asset into a pure text-and-code engine, rendering it significantly faster and lighter on consumer cards.

💻 Local Execution Guide (Target: GTX 1050 4GB VRAM)

When deploying this GGUF file inside Unsloth Desktop, LM Studio, Jan, or Ollama, configure these 3 runtime settings to prevent system stuttering:

GPU Offload: Set your hardware layer slider to 25 layers. This safely loads ~2.5 GB of the model weight into your NVIDIA GTX 1050 VRAM without freezing Windows, while the remaining compute safely overflows into your 16GB system RAM.
Sampling Settings: Set temperature=0.6, top_p=0.95, and top_k=20. Avoid a raw greedy search (temperature=0) to prevent the reasoning tokens from falling into endless structural loops.
Context Window: Set the token length to 16384 or 32768. This expanded context window allows autonomous agents to evaluate several source files at the same time.

🛠️ Execution with OpenCode Autonomous Agent

To launch this model as an active developer backend connected to your terminal agent, run the OpenAI-compatible local engine server:

unsloth start opencode --context-length 32000

Support / Donate

If this model helped you, consider supporting the project:

BTC: 18cBC5sFjtctw121ULTkxTbTZPurginJBs
LTC: ltc1q3jrcwrx66xpz4k92p08u8c5v8zwywk3dqpzdkv
USDT: TGKVpbbznmvEusKbuZZj4WSK6XxtHcG6FE (TRX chain)
USDT: 0x1059cb5a1F8467e5b56a9bdf082cE86FFB002D15 (POL chain)
USDT: 0x18b2AA731daeFD47DFFa278f3F856eAF80376fd6 (ETH chain)
USDT: 0x3bEcddC7c49bDba5503eB1677628b4519439884c (BNB chain)

Provenance & Licensing

Quantizations are built upon empero-ai/Qwen3.8-4B-Distill. Weights inherit the permissive Apache-2.0 license from the base Qwen repository and are shared as-is.

Downloads last month: 85

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

6-bit

Model tree for iBotIA/Qwen3.8-4B-Empero-AI-FullStack-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

empero-ai/Qwen3.8-4B-Distill

Quantized

(18)

this model