---
title: Scottzilla Gateway
emoji: ⚡
colorFrom: purple
colorTo: red
sdk: docker
app_port: 11434
pinned: true
---

# ⚡ Scottzilla Gateway

**Ollama-compatible API gateway** that unifies all ScottzillaSystems models — abliterated, uncensored, vision, code, and creative writing models — behind a single endpoint.

## API Endpoints

| Endpoint | Description |
|---|---|
| `GET /api/tags` | List all available models (Ollama format) |
| `GET /v1/models` | List all available models (OpenAI format) |
| `POST /api/chat` | Chat completion (Ollama format) |
| `POST /api/generate` | Text generation (Ollama format) |
| `POST /v1/chat/completions` | Chat completion (OpenAI format) |
| `GET /api/library` | Full model catalog with metadata, sizes, capabilities |
| `GET /` | Health check + system status |

## Connect from Anywhere

```bash
# Use as Ollama server
export OLLAMA_HOST=https://ScottzillaSystems-scottzilla-gateway.hf.space

# Use with OpenAI SDK
from openai import OpenAI
client = OpenAI(
    base_url="https://ScottzillaSystems-scottzilla-gateway.hf.space/v1",
    api_key="your-hf-token"
)

# Use with curl
curl https://ScottzillaSystems-scottzilla-gateway.hf.space/v1/chat/completions \
  -H "Authorization: Bearer $HF_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "cydonia-24b", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Model Catalog (17 models)

### Text Generation / Chat
| Alias | Model | Params | Type |
|---|---|---|---|
| `chatgpt-5` | ScottzillaSystems/ChatGPT-5 | 494M | Fast chat |
| `cydonia-24b` | ScottzillaSystems/Cydonia-24B-v4.1 | 23.6B | Creative writing |
| `qwen3.5-9b` | ScottzillaSystems/Qwen3.5-9B | 9.7B | Vision + language |
| `qwen3.5-40b-uncensored` | ScottzillaSystems/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking | 40B | Uncensored thinking |
| `gemma4-31b-abliterated` | ScottzillaSystems/Gemma-4-31B-JANG_4M-CRACK | 31B | Abliterated |
| `gemma4-31b-gguf` | ScottzillaSystems/Gemma-4-31B-it-abliterated | 31B | GGUF abliterated |
| `qwen3-coder-abliterated` | ScottzillaSystems/Huihui-Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-abliterated | - | Code + reasoning |
| `qwen3-vl-8b-abliterated` | ScottzillaSystems/Huihui-Qwen3-VL-8B-Instruct-abliterated | 8B | Vision abliterated |
| `qwen3.5-9b-abliterated` | ScottzillaSystems/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated | 9B | Abliterated |
| `qwen3.6-27b-abliterated` | ScottzillaSystems/Huihui-Qwen3.6-27B-abliterated | 27B | Abliterated |
| `qwen3.6-35b-abliterated` | ScottzillaSystems/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated | 35B MoE | Abliterated + LoRA |
| `qwen3.6-35b-mlx` | ScottzillaSystems/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit | 35B MoE | MLX 8-bit |
| `supergemma4-abliterated` | ScottzillaSystems/supergemma4-e4b-abliterated | - | Abliterated |
| `fallen-command-111b` | ScottzillaSystems/Fallen-Command-A-111B-v1_Compresses-Tensors | 111B | AWQ quantized |

### Image Generation
| Alias | Model | Type |
|---|---|---|
| `qwen-image-edit-nsfw` | ScottzillaSystems/qwen-image-edit-plus-nsfw-lora | NSFW image edit LoRA |
| `qwen-image-edit-nsfw-v2` | ScottzillaSystems/qwen-image-edit-plus-nsfw-lora2 | NSFW image edit LoRA v2 |