---

base_model: simpledirect/Vinci-Bozza-1.0

pipeline_tag: text-generation

tags:

- gguf

- quantized

- qwen3_5

- conversational

- chat

- character

- constitutional-ai

- simpledirect

- vinci

license: apache-2.0

---

<img src="./assets/vinci-vero-header.svg" alt="Vinci with Vero, its character" width="280" height="64">

Vinci Bozza 1.0 — GGUF

GGUF quantizations of simpledirect/Vinci-Bozza-1.0 for local inference with Ollama, LM Studio, and llama.cpp.

Text-only. The source model is multimodal (image-text-to-text); these GGUF conversions include the language model only — no mmproj / vision projector. For image input, use the safetensors build: simpledirect/Vinci-Bozza-1.0.

These files are not the measured artifact

🔴 No GGUF file in this repository has been evaluated. The benchmark figures on the full-precision card were measured on the unquantized bf16 weights, not on any file here. Quantization shifts scores, and with no per-tier measurement this card cannot say in which direction or by how much for any tier.

This card therefore publishes no per-tier score, no quality ranking between the tiers, and no recommended tier. The file sizes and memory figures below are measured, and describe storage and memory cost only. A file's presence in this repository is not a performance claim about that tier, and not a claim of parity with the full-precision weights.

Variants

| File | Size | Notes |

|---|---|---|

| Vinci-Bozza-1.0-Q6_K.gguf | ~6.8 GB | 6-bit K-quant |

| Vinci-Bozza-1.0-Q5_K_M.gguf | ~6.0 GB | 5-bit K-quant, medium mixture |

| Vinci-Bozza-1.0-Q4_K_M.gguf | ~5.2 GB | 4-bit K-quant, medium mixture |

Quick start

# Ollama — default quant auto-selected
ollama run hf.co/simpledirect/Vinci-Bozza-1.0-GGUF

# Specific quant
ollama run hf.co/simpledirect/Vinci-Bozza-1.0-GGUF:Q5_K_M

llama.cpp:

llama-cli -m Vinci-Bozza-1.0-Q5_K_M.gguf --chat-template chatml -p "Hello, who are you?"

Hardware requirements

| Variant | GPU VRAM | System RAM (CPU-only) |

|---|---|---|

| Q6_K | 10 GB | 16 GB |

| Q5_K_M | 8 GB | 14 GB |

| Q4_K_M | 7 GB | 12 GB |

Mac M-series: Q5_K_M runs comfortably on 16 GB unified memory; Q6_K needs 24 GB.

Prompt format

Uses Qwen / ChatML chat template. Pass enable_thinking=False (or equivalent) to suppress <think> blocks for normal chat use.

Links

• Full model (safetensors, BF16): simpledirect/Vinci-Bozza-1.0
• GitHub: https://github.com/getsimpledirect
• The Constitution: https://guide.getsimpledirect.com/constitution