# MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model

Digest AI · Research · published 2026-10-25T02:30:18Z

Canonical: https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz

## 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.

## Key points

- 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

## Why it matters

Provides a reproducible, pinned workflow for evaluating quantized tool-calling models locally, useful for developers choosing between compression methods.

## Sources

1. [How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide](https://marktechpost.com/2026/10/24/underdog-saluki-27b-coding-guide-llama-cpp) (MarkTechPost, 2026-10-25)

## Cite

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

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. 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
JSON: https://digestai.news/story/marktechpost-publishes-tutorial-on-running-underdog-saluki-27b-quantiz.json