UkisAI
UkisAI is an entity associated with the development and benchmarking of specialized Large Language Models (LLMs), specifically the Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF model family.
Benchmarks & Performance
Swift 1.5 Qwen3.8-27B GSQ-RCO IQ3_S 16GB LLM Performance Benchmark
Detailed evaluation of the Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF model’s IQ3_S quantization performance.
- Source: Swift 1.5 Qwen3.8-27B GSQ-RCO IQ3_S 16GB LLM Performance Benchmark
- Author: Luke’s Dev Lab
- Date: 2026-10-06
- Hardware Context: Local Ubuntu server setup with RTX 2000 Ada (16GB VRAM) GPU.
- Key Findings:
- Comprehensive benchmarking of the Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF model.
- Focus on IQ3_S quantization efficiency within 16GB VRAM constraints.
- Wide array of performance tests conducted to evaluate local LLM capabilities.