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 Learning2 min read

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Covered by 5 sources

OpenAI Resumes Training AI, But Without Internet Access

Covered by 4 sources
Machine Learning4 min read

OpenAI makes its Jev competitor widely available as decision model competition heats up

Covered by 3 sources