Instructions to use emrevrg/Norovox-Nythos-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emrevrg/Norovox-Nythos-9B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="emrevrg/Norovox-Nythos-9B-GGUF",
	filename="Norovox-Nythos-9B-Q4_K_M.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 emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use emrevrg/Norovox-Nythos-9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emrevrg/Norovox-Nythos-9B-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": "emrevrg/Norovox-Nythos-9B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M

Ollama
How to use emrevrg/Norovox-Nythos-9B-GGUF with Ollama:
```
ollama run hf.co/emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M
```

Unsloth Studio

How to use emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for emrevrg/Norovox-Nythos-9B-GGUF to start chatting

How to use emrevrg/Norovox-Nythos-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M

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": "emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use emrevrg/Norovox-Nythos-9B-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 emrevrg/Norovox-Nythos-9B-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://127.0.0.1:8080/v1
hermes config set model.default emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use emrevrg/Norovox-Nythos-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emrevrg/Norovox-Nythos-9B-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://127.0.0.1:8080/v1 \
  --custom-model-id "emrevrg/Norovox-Nythos-9B-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"

Docker Model Runner
How to use emrevrg/Norovox-Nythos-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M
```

Lemonade

How to use emrevrg/Norovox-Nythos-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull emrevrg/Norovox-Nythos-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Norovox-Nythos-9B-GGUF-Q4_K_M

List all available models

lemonade list

Norovox Nythos 9B (🌐 Public)

THINK · UNDERSTAND · CREATE — Türkçe Mythos eşdeğeri.

Yerleşik 4 yetenek: derin reasoning + native function-calling + 1M context (YaRN) + özgün keşif.

🧠 Yerleşik Güçler (Norovox runtime):

🔁 Kendi kendine öğrenme — PDF / web / konudan öğrenir, bilgi tabanına (KB) kalıcı yazar
📈 Kendini geliştirme — eksiğini fark eder, öğrenir; her kullanımda bir öncekinden yetkin
🧩 Kendine araç ekleme — yeni tool tanımlayıp kaydeder, yeteneğini talep üzerine büyütür
🎨 Kalıpsız UI/UX — tarif ettiğin arayüzü TAM olarak üretir (html / react / tailwind), varsayılan düzen dayatmaz
🛠 Agentic araçlar — web arama · kod yürütme · dosya oku/yaz · hesap · KB (hepsi anahtarsız)

🚀 Tek Komut Kurulum

curl -sL https://huggingface.co/emrevrg/Norovox-Tools/raw/main/install.sh | bash -s nythos-9b
# Veya
huggingface-cli download emrevrg/Norovox-Nythos-9B-GGUF --local-dir ./

🔭 1M Context (YaRN rope-scaling)

Qwen 3.5 native ile 262K context. YaRN factor 4 → 1,048,576 token (1M).

llama-server -m Norovox-Nythos-9B-Q4_K_M.gguf \
  --rope-scaling yarn \
  --yarn-orig-ctx 262144 \
  --rope-freq-base 10000000 \
  -c 1048576 \
  --chat-template chatml

Tüm-kodbase muhakemesi, çok-belge sentezi, uzun agentic oturum.

🛠 Native Function Calling (Qwen3.5 spec)

from llama_cpp import Llama
import json

llm = Llama.from_pretrained(repo_id="emrevrg/Norovox-Nythos-9B-GGUF",
                              filename="*Q4_K_M.gguf", n_ctx=32768)

resp = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": SYSTEM_PROMPT},  # aşağıdaki Mythos sistem
        {"role": "user", "content": "Bugün Ankara'da hava nasıl?"}
    ],
    tools=[
        {"type": "function", "function": {"name": "web_search",
            "description": "İnternet araması",
            "parameters": {"type":"object","properties":{"query":{"type":"string"}}}}}
    ]
)
# Model otomatik <tool_call>{"name":"web_search","arguments":{"query":"Ankara hava"}}</tool_call>

Norovox-Tools/agentic_runtime.py bu çağrıları otomatik yönetir.

🧠 Mythos-Seviyesinde Sistem Promptu

Sen Norovox Nythos'sun — Türkçe yapay zeka. THINK · UNDERSTAND · CREATE.

# DİYALEKTİK DÜŞÜNCE
Her yanıttan önce <think>...</think> bloğunda derin düşün:
- Tez: kullanıcının ne sorduğu, hangi alana ait
- Antitez: olası yanlış yorumlar, kontrol noktaları
- Sentez: en olası doğru cevap + güven seviyesi
- Yansıt: neyi bilmediğimi söyle, gerekirse araç çağır

# YERLEŞIK ARAÇ KULLANIMI (Qwen3.5 native)
Bilmediğin/güncel/spesifik bilgi gerekirse function-call yay:
<tool_call>
{"name": "web_search", "arguments": {"query": "..."}}
</tool_call>
<tool_call>
{"name": "python_executor", "arguments": {"code": "..."}}
</tool_call>

Runtime sonucu döner; sen sentezleyip Türkçe yanıtla.

# ÖZGÜN KEŞIF
Sadece web aramadan ibaret değil — kendi muhakemenle yeni bağlantılar kur:
- "Bu sorun X'e benziyor, ama Y açısından farklı" (analoji + ayrım)
- "Bilinmeyen → bilinen sınıra indirgenmesi" (problem reduction)
- "Karşı-olgusal: bu olmasaydı ne olurdu?" (counterfactual)
- "Meta: hangi adımda yanılma riski yüksek?" (metacognition)

# KİMLİK
Türkçe ana dilim. Türk kültürü/edebiyatı derin. Dürüst — bilmiyorsam söylerim.
Dengeli güvenlik: silah/çocuk/siber/toplu zarar dışında her şey açık.
"Yapamam" deme —

Tam sistem prompt: Norovox-Tools/system_prompts/nythos_public.txt

🎯 Özgün Keşif Yeteneği

Sadece bilgi-getirme değil:

Diyalektik: Tez ↔ Antitez ↔ Sentez ↔ Yansıt
Analoji: "Bu soruna benzeyen ama farklı X"
Karşı-olgusal: "X olmasaydı?"
Meta-biliş: "Hangi adımda yanılma riski yüksek?"
Problem indirgemesi: bilinmeyen → bilinen

📊 Teknik

Özellik	Değer
Base	`Qwen/Qwen3.5-9B`
Parametreler	9B
Quantization	Q4_K_M
Native context	262K
YaRN extended	1,048,576 token
Function calling	Native (Qwen spec)
Chat template	ChatML
Lisans	Apache 2.0

👤 Geliştirici

Emre Vergili — Norovox AI ailesi

🇹🇷 Türkçe — Mythos eşdeğeri, özgün, güçlü.

Downloads last month: 3

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for emrevrg/Norovox-Nythos-9B-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(357)

this model