GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

simpledirect/Vinci-Prova-7B-1.0-GGUF overview

<p align="center" Vinci https://vinci assets.s3.ca central 1.amazonaws.com/Vinci/logo+design/PNG/hf dark logo.png hf light mode only Vinci https://vinci assets…

ggufquantizedvinciprovabase_model:simpledirect/Vinci-Prova-7B-1.0base_model:quantized:simpledirect/Vinci-Prova-7B-1.0license:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~4.07 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
124
Likes
0
Pipeline

Repository Files & Downloads

4 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Vinci-Prova-7B-1.0-Q4_K_M.ggufGGUFQ4_K_M4.07 GBDownload
Vinci-Prova-7B-1.0-Q5_K_M.ggufGGUFQ5_K_M4.78 GBDownload
Vinci-Prova-7B-1.0-Q8_0.ggufGGUFQ8_07.17 GBDownload
Vinci-Prova-7B-1.0-f16.ggufGGUFF1613.50 GBDownload

Model Details

Model IDsimpledirect/Vinci-Prova-7B-1.0-GGUF
Authorsimpledirect
Pipeline
Licenseapache-2.0
Base modelsimpledirect/Vinci-Prova-7B-1.0
Last modified2026-08-13T19:13:30.000Z

Model README

---

license: apache-2.0

base_model: simpledirect/Vinci-Prova-7B-1.0

tags:

- gguf

- quantized

- vinci

- prova

---

<p align="center">

!Vinci

!Vinci

</p>

Vinci Prova 7B 1.0 - GGUF

Quantised GGUF builds of

simpledirect/Vinci-Prova-7B-1.0.

| file | quantisation | sha256 |

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

| Vinci-Prova-7B-1.0-f16.gguf | f16 (unquantised conversion) | 195460f2f2fbf033f5bee226903a9ab51591d26f62f6cd83702867e5d66f9e03 |

| Vinci-Prova-7B-1.0-Q4_K_M.gguf | Q4_K_M | 655886167ea8f07877954ee949b205557eb810774860535b84aa41c3446ca750 |

| Vinci-Prova-7B-1.0-Q5_K_M.gguf | Q5_K_M | ed521b15992b6716042e6bae4a9785bd1827ec05bf99661473adeb035c830f1b |

| Vinci-Prova-7B-1.0-Q8_0.gguf | Q8_0 | b0b724b4dd77d132f47ed364fed7053fc0dfa30edb4839cc07212ec0f206b9dc |

Verify what you downloaded against these hashes. Equal file size is not identity.

All evaluation results, limitations, intended use and provenance live on the main repo.

Read its model card before using these builds. Nothing is restated here, so there is one

place for a number to be correct. The full study is published as

Vinci Technical Report No. 1 (CC BY 4.0).

Quantisation changes model behaviour. Every published measurement was taken on the

unquantised weights in the main repo, not on these files.

Run simpledirect/Vinci-Prova-7B-1.0-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models