---
license: apache-2.0
library_name: gguf
tags:
  - coding
  - code-generation
  - qwen3
  - gguf
  - cortiq
language:
  - en
base_model: Qwen/Qwen3-27B
---

# Cortiq Coder 12B

**Cortiq Coder 12B** is a task-specialized coding model compiled from [Qwen3-27B](https://huggingface.co/Qwen/Qwen3-27B) down to ~12B effective parameters using a proprietary dynamic neural network compression method developed by [AllAIGate](https://allaigate.com).

The compression is performed via the **CORTIQ** method — a system and method for **Dynamic Task-Guided Neural Network Compression with Catastrophic Forgetting Prevention**, covered under **US Patent Application No. 19/452,464** (filed January 19, 2026).

Unlike naive pruning or quantization, CORTIQ preserves task-critical knowledge during compression by dynamically guiding the pruning process toward the target domain (code generation), while actively preventing degradation of the model's core reasoning capabilities.

## Key Features

- 🔧 **Optimized for code generation** — structured compression guided by coding tasks
- 🧠 **Based on Qwen3-27B** — retains strong reasoning foundation of the 27B base model at 12B scale
- 🚀 **GGUF Q4_K_M quantization** — ready for efficient local inference
- 🛡️ **Catastrophic forgetting prevention** — task-specific compression without degrading general capabilities
- 📦 **Compact footprint** — 9.37 GB in GGUF Q4_K_M format

## Files

| File | Format | Size | Description |
|------|--------|------|-------------|
| `cortiq-coder-12b-Q4_K_M.gguf` | GGUF | 9.37 GB | Quantized model for llama.cpp / LM Studio / Ollama |
| `cortiq-coder-12b-nvg.tar` | TAR | 30.1 GB | Full native model weights |

## Quick Start

### llama.cpp
```bash
llama-server -hf infosave/cortiq-coder-12B:Q4_K_M
```

### Ollama
```bash
ollama run hf.co/infosave/cortiq-coder-12B:Q4_K_M
```

### Python (llama-cpp-python)
```python
from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="infosave/cortiq-coder-12B",
    filename="cortiq-coder-12b-Q4_K_M.gguf",
)
response = llm.create_chat_completion(messages=[
    {"role": "user", "content": "Write a Python function to sort a list of dicts by key."}
])
print(response["choices"]["message"]["content"])
```

## Method Reference

> **Patent:** US Application No. 19/452,464 — *"System and Method for Dynamic Task-Guided Neural Network Compression with Catastrophic Forgetting Prevention"* — Filed January 19, 2026.  
> **Details:** [https://allaigate.com/ru/](https://allaigate.com)

## License

Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), consistent with the Qwen3 base model license.