You can deploy this model and start earning money today!

simpledirect/
Vinci-Bozza-1.0-GGUF

Name: Vinci-Bozza-1.0-GGUF
Availability: InStock

simpledirect/Vinci-Bozza-1.0

quantized

apache-2.0

endpoints_compatible

Views

No views yet

Vinci

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.

Variants

File	Size	Notes
`Vinci-Bozza-1.0-Q6_K.gguf`	~6.8 GB	Closest to BF16 quality
`Vinci-Bozza-1.0-Q5_K_M.gguf`	~6.0 GB	Good balance (recommended)
`Vinci-Bozza-1.0-Q4_K_M.gguf`	~5.2 GB	Smallest, tight memory budgets

Quick start

bash

# Ollama — recommended 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.

simpledirect/Vinci-Bozza-1.0-GGUF