simpledirect/Vinci-Prova-7B-1.0-GGUF overview
<img src="./assets/vinci vero header.svg" alt="Vinci with Vero, its character" width="280" height="64" Vinci Prova 7B 1.0 GGUF Quantised GGUF builds of simpled…
Runs locally from ~4.07 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | simpledirect/Vinci-Prova-7B-1.0-GGUF |
|---|---|
| Author | simpledirect |
| Pipeline | — |
| License | apache-2.0 |
| Base model | simpledirect/Vinci-Prova-7B-1.0 |
| Last modified | 2026-09-28T03:30:58.000Z |
Model README
---
license: apache-2.0
base_model: simpledirect/Vinci-Prova-7B-1.0
tags:
- gguf
- quantized
- vinci
- prova
---
<img src="./assets/vinci-vero-header.svg" alt="Vinci with Vero, its character" width="280" height="64">
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.
These files are not the measured artifact
🔴 No GGUF file in this repository has been evaluated. Every published measurement was taken on the unquantised weights in the main repo, not on any file here. Quantisation changes model behaviour, 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. A file's presence in this repository is not a performance claim about that tier, and not a claim of parity with the unquantised weights.
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).
Follow-up, 1 September 2026. Technical Report No. 2
applied the same frozen recipe to three model families and did not establish general
cross-lineage portability. The Report No. 1 measurements are unchanged. Both reports are
summarised on the main repo's card; nothing is restated here.
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.
Source: Hugging Face · Compare models