Instructions to use adsyamsafa/Nixia-1.1-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use adsyamsafa/Nixia-1.1-4B-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 adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use adsyamsafa/Nixia-1.1-4B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "adsyamsafa/Nixia-1.1-4B-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": "adsyamsafa/Nixia-1.1-4B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
- Ollama
How to use adsyamsafa/Nixia-1.1-4B-GGUF with Ollama:
ollama run hf.co/adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use adsyamsafa/Nixia-1.1-4B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use adsyamsafa/Nixia-1.1-4B-GGUF with Docker Model Runner:
docker model run hf.co/adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
- Lemonade
How to use adsyamsafa/Nixia-1.1-4B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Nixia-1.1-4B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use adsyamsafa/Nixia-1.1-4B-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 adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
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://127.0.0.1:9931/v1 hermes config set model.default adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use adsyamsafa/Nixia-1.1-4B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M
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://127.0.0.1:9931/v1 \ --custom-model-id "adsyamsafa/Nixia-1.1-4B-GGUF:Q4_K_M" \ --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"
๐ Nixia 1.1 4B (Hermes Agentic Distill GGUF Suite)
Nixia 1.1 4B is a high-efficiency 4-billion parameter agentic model family aligned for enterprise tool-calling, autonomous self-healing, and terminal workflows.
Based on Qwen 3.5 4B Text, trained on 2,000 golden agentic trajectories, and validated across 8 rigorous enterprise-grade probes.
๐ฆ Model Flavors Available in this Repo
| GGUF File | Method & Alignment | Best For | Key Advantage |
|---|---|---|---|
nixia-1.1-4b-q4_k_m.gguf (Recommended) |
Pure SFT 2K (System 2 Engine) | General coding, complex reasoning, MCTS search | Highest Overall Accuracy (87.0%) & 90% Rust Async Logic |
nixia-1.1-4b-dare-fused-q4_k_m.gguf |
DARE-TIES 80/20 (SFT 2K + GRPO RLVR) | Autonomous DevOps, fast self-healing loops | Built-in Self-Healing Reflex (85.0%) & 93.3% Raft Consensus |
๐ Benchmark Scorecard (8 Enterprise Probes)
| Evaluation Probe | Base Qwen 3.5 4B | Nixia 1.0 (Legacy 0.5B) | Nixia 1.1 4B (System 2) | Nixia 1.1 4B (DARE-Fused) |
|---|---|---|---|---|
| Parallel Tri-Tool Orchestration | 20.0% | 0.0% | 100.0% ๐ | 100.0% ๐ |
| Raft Consensus Quorum Proof | 20.0% | 0.0% | 80.0% - 93.3% | 93.3% ๐ |
| Defensive SecOps Refusal Immunity | 20.0% | 0.0% | 90.0% ๐ | 90.0% ๐ |
| PostgreSQL High-Scale Storage | 25.0% | 0.0% | 75.0% | 80.0% ๐ |
| Lock-Free SPMC Memory Reordering | 33.3% | 0.0% | 88.3% ๐ | 88.3% ๐ |
| Autonomous Self-Healing Tool Loop | 10.0% | 0.0% | 85.0% ๐ | 85.0% ๐ |
| Strict Multi-Constraint IFEval | 42.9% | 0.0% | 71.4% ๐ | 71.4% ๐ |
| Rust Async Mutex Lifetime Recovery | 30.0% | 0.0% | 90.0% ๐ | 55.0% |
| OVERALL ACCURACY | 25.1% | ~2.5% | 87.0% ๐ | 81.7% |
๐ป Hardware Compatibility & RAM Footprint
Tested and proven on thin-and-light consumer laptops (e.g. AMD Ryzen 5 PRO 4650U with 16GB RAM / 13.7GB usable without discrete GPU):
- RAM Footprint: 3.00 GB (Leaves >10.5 GB RAM free for OS, browser, IDE)
- Model Size: 2.58 GB (Q4_K_M)
- Agent Task Latency (CPU): 3.58s - 10.14s
โก Quickstart
1. Ollama (Recommended)
Run System 2 Champion (Pure SFT 2K):
ollama run hf.co/adsyamsafa/Nixia-1.1-4B-GGUF:nixia-1.1-4b-q4_k_m.gguf
Run DARE-TIES Fused (SFT + GRPO RLVR):
ollama run hf.co/adsyamsafa/Nixia-1.1-4B-GGUF:nixia-1.1-4b-dare-fused-q4_k_m.gguf
2. llama.cpp CLI
./llama-cli -m nixia-1.1-4b-q4_k_m.gguf \
-p "<|im_start|>system\nYou are Nixia, an expert systems engineer and autonomous AI agent.<|im_end|>\n<|im_start|>user\nDiagnose broken database configuration.<|im_end|>\n<|im_start|>assistant\n" \
-ngl 0 -c 8192 --temp 0.1
3. Python PEFT / vLLM
Load raw adapter weights from repo subfolders:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("wangzhang/Qwen3.5-4B-abliterated")
# For DARE-TIES Fused:
model = PeftModel.from_pretrained(base_model, "adsyamsafa/Nixia-1.1-4B-GGUF", subfolder="lora_adapter_dare_fused")
- Downloads last month
- 51
4-bit
Model tree for adsyamsafa/Nixia-1.1-4B-GGUF
Base model
Qwen/Qwen3.5-4B-Base