Machine LearningDev30 min reading time

How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide

MarkTechPost
Read the full article
Underdog Saluki 27B is a 7.9 GB quantized version of Qwen3.8-27B that maintains tool-calling capabilities at 2-bit precision and outperforms the full 54 GB model on a 120-task benchmark. The tutorial compares Saluki to ISTA-DASLab's GSQ-RCO quantization using llama.cpp, evaluating memory, speed, and task performance.

More in Machine Learning

Machine Learning3 min read

OpenAI Trumpets 3 More Math and Science Results, Along With a New Plan for Publishing Them

Covered by 2 sources
Machine Learning4 min read

OpenAI says its AI model has disproved the Exponential Time Hypothesis

The Next Web
Machine Learning3 min read

This AI startup raised $300 million to build digital versions of consumers

Business Insider