MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model
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…
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
How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide
MarkTechPost · 25 October 2026
Loading the full article…
This text was published by MarkTechPost and written by Sana Hassan. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Microsoft Open-Sources Agensh, a Multi-Agent harness for coding · 1 src
- OpenAI agents study Parkinson-like disease data in 32 minutes · 1 src
- OpenAI releases LASER to find ambiguous AI safety cases · 1 src
- Study finds AI text harder to read due to information density · 1 src
- OpenAI suspects three ex-researchers leaked internal model designs to Ryan Greenblatt · 2 src
Comments
via GitHub Discussions