{"version":1,"type":"story","url":"https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz","json":"https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz.json","markdown":"https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz.md","slug":"marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz","headline":"MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model","summary":"MarkTechPost published a technical tutorial demonstrating how to run Underdog Saluki 27B, a 7.9 GB quantized version of Qwen3.8-27B that claims to preserve tool-calling ability at roughly two bits per weight. Both models are served via llama.cpp b11565 on a single GPU and evaluated on 120 seeded tasks from the Berkeley Function Calling Leaderboard v4 using BFCL's own checker with strict and lenient parsing. The tutorial includes header diffs, byte-level provenance checks, memory and speed measurements, and re-run consistency tests. All downloads are pinned by size and hash to specific revisions.","keyPoints":["Both models tested on 120 BFCL v4 tasks with strict and lenient scoring using BFCL's own checker","All files pinned by SHA-256 to fixed Hugging Face revisions and gorilla commit 6ea5797"],"whyItMatters":"Provides a reproducible, pinned workflow for evaluating quantized tool-calling models locally, useful for developers choosing between compression methods.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["ConwayResearch","ISTA-DASLab","Hugging Face","MarkTechPost"],"models":["Underdog Saluki 27B","Qwen3.8-27B","Qwen3.8-27B-GSQ-RCO-IQ2XS"],"people":[]},"firstPublishedAt":"2026-10-25T02:30:18Z","updatedAt":"2026-10-25T02:30:18Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide","url":"https://marktechpost.com/2026/10/24/underdog-saluki-27b-coding-guide-llama-cpp","publishedAt":"2026-10-25T02:30:18Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model\", 25 October 2026, https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz","publisher":"Digest AI","title":"MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model","datePublished":"2026-10-25T02:30:18Z","url":"https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}