---
license: apache-2.0
tags:
  - gguf
  - osiris
  - llama.cpp
---

# OsirisCortex-v6-GGUF

GGUF quantized version of OsirisCortex-v6 (Qwen3.5-9B Identity Fusion, abliterated). For use with llama.cpp on Apple Silicon.

## Files

| File | Description |
|------|-------------|
| `OsirisCortex-v6-Q6_K.gguf` | GGUF quantized model |
| `OsirisCortex-v6-mmproj-BF16.gguf` | GGUF quantized model |

## Usage with llama.cpp

```bash
./llama-server -m <model-file>.gguf -ngl 99
```