cd /news/large-language-models/meet-the-underdog-saluki-27b-a-2-bit… · home › topics › large-language-models › article
[ARTICLE · art-148146] src=marktechpost.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling

Underdog Saluki 27B, a 7.89 GB 2-bit GGUF quantization of Qwen3.8-27B released under Apache 2.0, outperforms the 54 GB original model on tool calling while losing ground on competition math and reasoning, according to MarkTechPost. The release cuts the model's footprint to roughly one-seventh of the original's size.

by read1 min views1 publishedOct 9, 2026

Underdog Saluki 27B is a 7.89 GB, 2-bit GGUF of Qwen3.8-27B under Apache 2.0. It beats the 54 GB original on tool calling but gives up ground on competition math and reasoning.

The post Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling appeared first on MarkTechPost.

source & further reading
marktechpost.com — original article Google Research RRSI Guide: Mastering Self-Improving AI Agents JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents Architect Launches Liquid Inference, a Real-Time Auction for LLM Inference
── more in #large-language-models 4 stories · sorted by recency
── more on @underdog saluki 27b 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/meet-the-underdog-sa…] indexed:0 read:1min 2026-10-09 · —