CoolFace
Modelpublic

sigmanih/Qwen3.8-27B-GGUF-Q4_K_S

sourceHugging Faceotherupdated 2d agoView on Hugging Face
3likes824downloads
Model Card

<div align="center">

⚡ Qwen3.8-27B-GGUF-Q4KS

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/Qwen3.8-27B-GGUF-Q4KS) ![Engine](https://github.com/Sigmanih/SigmaStudio) ![License: Apache-2.0](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

Qwen3.8-27B-GGUF-Q4_K_S is a production-ready model optimized and published using the Model Hub module of [Sigma Studio](https://github.com/Sigmanih/SigmaStudio).

⚙️ Technical Specifications & Architecture

SpecificationValue
Model Repositorysigmanih/Qwen3.8-27B-GGUF-Q4_K_S
Weight FormatGGUF (Q4_K_S)
Base Architectureqwen35
Active Parameters27B
Context Window262,144 tokens
Transformer Layers65
Hidden Dimension5120
Total Disk Footprint14.74 GB
Inference RAM / VRAM`~15.8 GB VRAM` (Full GPU offload) / `~15.6 GB RAM` (CPU/Hybrid)
Recommended HardwareGPU with 16-20 GB VRAM (e.g. RTX 4080 or 32 GB RAM)
Recommended UsageAdvanced logic & reasoning, Enterprise domain specialization, Complex code refactoring.

⚡ Measured Speed on the Publishing Machine

No local speed measurement was recorded for this model: the figure below is an estimate for its size class, not a measurement.

What was measuredValueHow
Aggregate throughput during evaluation14.5 tok/sseveral 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/Qwen3.8-27B-GGUF-Q4_K_S -p "Hello! How can I help you today?" -ngl 99

🇮🇹 Documentazione in Italiano

Qwen3.8-27B-GGUF-Q4_K_S 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: qwen35 (27B parametri)
  • —Formato Pesi: GGUF (Q4KS)
  • —Spazio su Disco: 14.74 GB
  • —RAM / VRAM in Esecuzione: ~15.8 GB VRAM (offload GPU completo) | ~15.6 GB RAM (inferenza CPU/ibrida)
  • —Requisiti Hardware Consigliati: GPU con 16-20 GB VRAM (es. RTX 4080 o 32 GB RAM)
  • —Finestra di Contesto: 262,144 token
  • —Profilo d'Uso Consigliato: Logica e ragionamento avanzato, specializzazione di dominio enterprise, refactoring complesso.

⏱️ Throughput Hardware e Fasce Consigliate

  • —Velocità Stimata: ~14.5 tok/s per questa classe di dimensione — nessuna misura locale registrata.
  • —Throughput complessivo durante la valutazione: 14.5 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 (25/09/2026 20:09)