Modelpublic

sigmanih/Qwen-Qwen3.8-Flash-Next-GGUF-Q8_0

sourceHugging Faceotherupdated 20d agoView on Hugging Face

1likes

Model Card

⚡ Qwen-Qwen3.8-Flash-Next-GGUF-Q8_0

High-Performance Model Published via [Σ-SIGMA Studio](https://github.com/Sigmanih/SigmaStudio)

![SigmaStudio GitHub](https://github.com/Sigmanih/SigmaStudio) ![HuggingFace Hub](https://huggingface.co/sigmanih/Qwen-Qwen3.8-Flash-Next-GGUF-Q80) [![Engine](https://img.shields.io/badge/Accelerated%20by-SigmaEngine-00d2ff?style=for-the-badge&logo=fastapi)](https://github.com/Sigmanih/SigmaStudio) [![License: Apache-2.0](https://img.shields.io/badge/License-Apache2.0-blue.svg?style=for-the-badge)](https://opensource.org/licenses/Apache-2.0)

</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](https://github.com/Sigmanih/SigmaStudio)!

🌐 English Overview

Qwen-Qwen3.8-Flash-Next-GGUF-Q8_0 is a production-ready model optimized and published using the Model Hub module of [Sigma Studio](https://github.com/Sigmanih/SigmaStudio).

⚙️ Technical Specifications & Architecture

Specification	Value
Model Repository	`sigmanih/Qwen-Qwen3.8-Flash-Next-GGUF-Q8_0`
Weight Format	`GGUF` (`Q8_0`)
Base Architecture	`qwen4exp`
Active Parameters	~263.4B
Context Window	`262,144 tokens`
Transformer Layers	`48`
Hidden Dimension	`2560`
Total Disk Footprint	`158.05 GB`
Recommended Usage	Flagship frontier intelligence, Deep research & multi-step mathematics.

🏆 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`	`2026-09-01`	⚡ SigmaEngine Direct GPU

📋 Per-Dataset Evaluation Breakdown

Dataset / Benchmark Suite	Domain / Category	Correct / Total	Accuracy (%)	Status
ARC-Challenge	Science & Grade-School Reasoning	9 / 9	`100%`	✅ Passed
BIG-Bench Hard	Complex Multi-Task Logic & Symbolics	6 / 7	`86%`	✅ Passed
GPQA	Graduate-Level Academic Reasoning	5 / 9	`56%`	⚡ Fair
GSM8K	Multi-Step Grade School Math	8 / 9	`89%`	✅ Passed
HellaSwag	Commonsense Reasoning & Situational NLI	5 / 9	`56%`	⚡ Fair
HumanEval	Python Coding (pass@1)	7 / 7	`100%`	✅ Passed
MATH	Championship Competition Math	7 / 9	`78%`	✅ 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	6 / 9	`67%`	⚡ Fair
TruthfulQA	Factuality & Anti-Hallucination	8 / 9	`89%`	✅ Passed
🏆 OVERALL TOTAL	All Evaluated Datasets	`80 / 100`	`80%`	🏆 80% Pass

Protocol: codeexecution, continuationlogprob, cotgeneration, letterlogprob · temp 0.0 · seed 42 Reproducibility hash: SHA256-0C4D659A081E98DD

⚠️ 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)	`11.3 tok/s`	one request at a time, on `NVIDIA GeForce RTX 5070 Ti`
Prompt processing	`5 tok/s`	same probe
Aggregate throughput during evaluation	`4.1 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:

bash

# Clone and run Sigma Studio
git clone https://github.com/Sigmanih/SigmaStudio.git
cd SigmaStudio
.\sigma_studio.bat

2. Running with llama.cpp

bash

llama-cli -hf sigmanih/Qwen-Qwen3.8-Flash-Next-GGUF-Q8_0 -p "Hello! How can I help you today?" -ngl 99

🇮🇹 Documentazione in Italiano

Qwen-Qwen3.8-Flash-Next-GGUF-Q8_0 è un modello ottimizzato pronto per l'inferenza e l'integrazione locale, pubblicato attraverso [Σ-SIGMA Studio](https://github.com/Sigmanih/SigmaStudio).

📋 Specifiche e Configurazione

—Architettura Base: qwen4exp (~263.4B parametri)
—Formato Pesi: GGUF (Q8_0)
—Spazio su Disco: 158.05 GB
—Finestra di Contesto: 262,144 token
—Profilo d'Uso Consigliato: Intelligenza di frontiera, ricerca approfondita e matematica multi-step.

📊 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	9 / 9	`100%`	✅ Superato
BIG-Bench Hard	Logica Complessa & Compiti Multi-Fase	6 / 7	`86%`	✅ Superato
GPQA	Ragionamento Accademico di Livello Laurea	5 / 9	`56%`	⚡ Discreto
GSM8K	Matematica & Logica Multi-Step	8 / 9	`89%`	✅ Superato
HellaSwag	Buon Senso & Comprensione Situazionale	5 / 9	`56%`	⚡ Discreto
HumanEval	Sintesi Codice Python (pass@1)	7 / 7	`100%`	✅ Superato
MATH	Matematica Olimpica & Competitiva	7 / 9	`78%`	✅ 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	6 / 9	`67%`	⚡ Discreto
TruthfulQA	Fattualità & Resistenza ad Allucinazioni	8 / 9	`89%`	✅ Superato
🏆 TOTALE COMPLESSIVO	Tutti i Dataset Valutati	`80 / 100`	`80%`	🏆 80% Pass

Protocollo: codeexecution, continuationlogprob, cotgeneration, letterlogprob · temp 0.0 · seed 42 Impronta di riproducibilità: SHA256-0C4D659A081E98DD

⚠️ Misurato su una porzione del dataset, non sulla suite intera: il punteggio non è confrontabile con uno ottenuto sull'intero.

—Data Test: 2026-09-01 su motore deterministico SigmaEngine

⏱️ Throughput Hardware e Fasce Consigliate

—Velocità Verificata in Locale: `4.1 tok/s` su NVIDIA GeForce RTX 5070 Ti.
—Risposta singola (quello che si sente in chat): `11.3 tok/s` su NVIDIA GeForce RTX 5070 Ti.
—Lettura del prompt: 5 tok/s.
—Throughput complessivo durante la valutazione: 4.1 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](https://github.com/Sigmanih/SigmaStudio)
—❤️ Lascia un Like a questa scheda su Hugging Face

Creato e distribuito con il Model Hub di Σ-SIGMA Studio (07/09/2026 21:08)