sigmanih/google-gemma-4-12B-it-GGUF-Q8_0 overview
<div align="center" ⚡ google gemma 4 12B it GGUF Q8 0 High Performance Model Published via Σ SIGMA Studio https://github.com/Sigmanih/SigmaStudio SigmaStudio G…
Runs locally from ~11.80 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| google--gemma-4-12B-it.Q8_0.gguf | GGUF | GGUF | 11.80 GB | Download |
Model Details
| Model ID | sigmanih/google-gemma-4-12B-it-GGUF-Q8_0 |
|---|---|
| Author | sigmanih |
| Pipeline | text-generation |
| License | other |
| Base model | google/gemma-4-12B-it |
| Last modified | 2026-08-31T20:34:53.000Z |
Model README
---
language:
- en
- it
license: other
base_model:
- google/gemma-4-12B-it
tags:
- text-generation
- sigma-studio
- sigmanih
- conversational
- custom-model
- gguf
- llama.cpp
- quantized
- q8_0
pipeline_tag: text-generation
---
<div align="center">
⚡ google-gemma-4-12B-it-GGUF-Q8_0
High-Performance Model Published via Σ-SIGMA Studio
   
</div>
> ❤️ Support & Community: If you find this model helpful, please give this repository a Like on Hugging Face and a ⭐ Star on our SigmaStudio GitHub!
🌐 English Overview
google-gemma-4-12B-it-GGUF-Q8_0 is a production-ready model optimized and published using the Model Hub module of Sigma Studio.
⚙️ Technical Specifications & Architecture
| Specification | Value |
| :--- | :--- |
| Model Repository | sigmanih/google-gemma-4-12B-it-GGUF-Q8_0 |
| Weight Format | GGUF (Q8_0) |
| Base Architecture | gemma4 |
| Active Parameters | 12B |
| Context Window | 262,144 tokens |
| Transformer Layers | 48 |
| Hidden Dimension | 3840 |
| Total Disk Footprint | 11.8 GB |
| Recommended Usage | High-speed coding, Everyday assistants, Autonomous agentic loops & reasoning. |
🏆 Official Benchmark Performance
Evaluated directly on GPU via Sigma Studio Training Lab (Deterministic seed 42, Temp 0.0):
| Benchmark Suite | Score / Accuracy | Total Questions Evaluated | Pass Rate | Test Date | Execution Engine |
| :--- | :---: | :---: | :---: | :---: | :---: |
| Tutti i Benchmark Ufficiali | 80.0% | 80/100 quesiti superati | 80.0% Pass | 2026-08-30 | ⚡ SigmaEngine Direct GPU |
📋 Per-Dataset Evaluation Breakdown
| Dataset / Benchmark Suite | Domain / Category | Correct / Total | Accuracy (%) | Status |
| :--- | :--- | :---: | :---: | :---: |
| ARC-Challenge | Science & Grade-School Reasoning | 8 / 9 | 89% | ✅ Passed |
| BIG-Bench Hard | Complex Multi-Task Logic & Symbolics | 7 / 7 | 100% | ✅ Passed |
| GPQA | Graduate-Level Academic Reasoning | 3 / 9 | 33% | ⚠️ Low |
| GSM8K | Multi-Step Grade School Math | 8 / 9 | 89% | ✅ Passed |
| HellaSwag | Commonsense Reasoning & Situational NLI | 5 / 9 | 56% | ⚡ Fair |
| HumanEval | Python Coding (pass@1) | 6 / 7 | 86% | ✅ Passed |
| MATH | Championship Competition Math | 8 / 9 | 89% | ✅ Passed |
| MBPP | Python Programming with Unit Tests | 8 / 9 | 89% | ✅ Passed |
| MMLU | General Knowledge & Multi-Subject | 11 / 14 | 79% | ✅ Passed |
| MMLU-Pro | Advanced Multi-Step Reasoning | 7 / 9 | 78% | ✅ Passed |
| TruthfulQA | Factuality & Anti-Hallucination | 9 / 9 | 100% | ✅ Passed |
| 🏆 OVERALL TOTAL | All Evaluated Datasets | 80 / 100 | 80% | 🏆 80% Pass |
Protocol: code_execution, continuation_logprob, cot_generation, letter_logprob · temp 0.0 · seed 42
Reproducibility hash: SHA256-B81232ECC62AC6FC
> ⚠️ Measured on a slice of the dataset, not the full suite: this score is not comparable with a full-suite run.
⚡ Measured Speed on the Publishing Machine
Measured on NVIDIA GeForce RTX 5070 Ti • 15.9 GB VRAM. Two different numbers follow, and they are not interchangeable.
| What was measured | Value | How |
| :--- | :---: | :--- |
| Single-stream decode (what a chat feels) | 38.9 tok/s | one request at a time, on NVIDIA GeForce RTX 5070 Ti |
| Prompt processing | 344 tok/s | same probe |
| Aggregate throughput during evaluation | 40.4 tok/s | several requests in flight — not what a single answer runs at |
> Speeds on other hardware were not measured and are not guessed here. A single-stream figure from one machine cannot be scaled into a prediction for another: it depends on memory bandwidth, quantization, context length and driver, and the error is large enough to be misleading.
🚀 Quick Start Guide
1. Running with Sigma Studio (Recommended)
Launch Sigma Studio to enjoy full 1-click GPU hardware acceleration, live monitoring, and visual chat:
# Clone and run Sigma Studio
git clone https://github.com/Sigmanih/SigmaStudio.git
cd SigmaStudio
.\sigma_studio.bat2. Running with llama.cpp
llama-cli -hf sigmanih/google-gemma-4-12B-it-GGUF-Q8_0 -p "Hello! How can I help you today?" -ngl 99---
🇮🇹 Documentazione in Italiano
google-gemma-4-12B-it-GGUF-Q8_0 è un modello ottimizzato pronto per l'inferenza e l'integrazione locale, pubblicato attraverso Σ-SIGMA Studio.
📋 Specifiche e Configurazione
- Architettura Base:
gemma4(12B parametri) - Formato Pesi:
GGUF(Q8_0) - Spazio su Disco:
11.8 GB - Finestra di Contesto:
262,144 token - Profilo d'Uso Consigliato: Coding ad alta velocità, assistenti quotidiani, loop di agenti autonomi e ragionamento.
📊 Risultati Benchmark Ufficiali
- Suite di Valutazione:
Tutti i Benchmark Ufficiali - Punteggio Ufficiale:
80.0%(80/100 quesiti superati)
📋 Dettaglio Punteggi per Singolo Dataset
| Dataset / Suite di Test | Ambito / Dominio | Corretti / Totale | Accuratezza (%) | Esito |
| :--- | :--- | :---: | :---: | :---: |
| ARC-Challenge | Ragionamento Scientifico Avanzato | 8 / 9 | 89% | ✅ Superato |
| BIG-Bench Hard | Logica Complessa & Compiti Multi-Fase | 7 / 7 | 100% | ✅ Superato |
| GPQA | Ragionamento Accademico di Livello Laurea | 3 / 9 | 33% | ⚠️ Migliorabile |
| GSM8K | Matematica & Logica Multi-Step | 8 / 9 | 89% | ✅ Superato |
| HellaSwag | Buon Senso & Comprensione Situazionale | 5 / 9 | 56% | ⚡ Discreto |
| HumanEval | Sintesi Codice Python (pass@1) | 6 / 7 | 86% | ✅ Superato |
| MATH | Matematica Olimpica & Competitiva | 8 / 9 | 89% | ✅ Superato |
| MBPP | Programmazione Python con Unit Test | 8 / 9 | 89% | ✅ Superato |
| MMLU | Conoscenza Generale Multidisciplinare | 11 / 14 | 79% | ✅ Superato |
| MMLU-Pro | Ragionamento Avanzato Multi-Step | 7 / 9 | 78% | ✅ Superato |
| TruthfulQA | Fattualità & Resistenza ad Allucinazioni | 9 / 9 | 100% | ✅ Superato |
| 🏆 TOTALE COMPLESSIVO | Tutti i Dataset Valutati | 80 / 100 | 80% | 🏆 80% Pass |
Protocollo: code_execution, continuation_logprob, cot_generation, letter_logprob · temp 0.0 · seed 42
Impronta di riproducibilità: SHA256-B81232ECC62AC6FC
> ⚠️ Misurato su una porzione del dataset, non sulla suite intera: il punteggio non è confrontabile con uno ottenuto sull'intero.
- Data Test:
2026-08-30su motore deterministico SigmaEngine
⏱️ Throughput Hardware e Fasce Consigliate
- Velocità Verificata in Locale:
40.4 tok/ssuNVIDIA GeForce RTX 5070 Ti. - Risposta singola (quello che si sente in chat):
38.9 tok/ssuNVIDIA GeForce RTX 5070 Ti. - Lettura del prompt:
344 tok/s. - Throughput complessivo durante la valutazione:
40.4 tok/s— piu' richieste in volo insieme, non la velocita' di una risposta singola. - Le velocita' su altro hardware non sono state misurate e non vengono indovinate: dipendono da banda di memoria, quantizzazione, lunghezza del contesto e driver.
⭐ Supporta il Progetto Open Source
Se questo modello ti è utile o vuoi esplorare l'ecosistema completo:
- 🌟 Metti una Stella al repository GitHub: Sigmanih/SigmaStudio
- ❤️ Lascia un Like a questa scheda su Hugging Face
---
Creato e distribuito con il Model Hub di Σ-SIGMA Studio (31/08/2026 22:34)
Run sigmanih/google-gemma-4-12B-it-GGUF-Q8_0 with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models