Underdog-Saluki-27B trends on Hugging Face with 2-bit GGUF quants and tool calling

ConwayResearch · hf · 2026-10-09

Underdog-Saluki-27B-1.0 is trending on Hugging Face as a text-generation model. Built on ISTA-DASLab/Qwen3.8-27B, it ships GGUF quantizations down to 2-bit while retaining tool-calling and function-calling support, targeting local llama.cpp deployments and agent workflows.

Original post →

More from Models

Models channel →