# Saluki 27B: 2‑bit Qwen3.8 model outperforms original on tool calling

> The open‑source Saluki 27B model, only 7.89 GB, beats the full‑size Qwen3.8‑27B at tool‑calling tasks.

Oossa · 2026-10-09 · https://oossa.com/en/saluki-27b-2-bit-qwen3-8-model-outperforms-original-on-tool-calling

The community‑released Saluki 27B is a 2‑bit GGUF version of Qwen3.8‑27B. It is 7.89 GB in size and licensed under Apache 2.0. According to the MarkTechPost article, Saluki beats the original 54 GB model on tool‑calling benchmarks, though it lags behind on competition‑math and reasoning tests.

## The facts

- Size: 7.89 GB (2‑bit GGUF) – 54 GB original model is larger
- Performance: better at tool‑calling, weaker on competition math and reasoning

## Why it matters

Developers can run a much smaller, freely licensed model that handles tool‑calling more effectively on modest hardware.

## Sources & references

1. [Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling](https://www.marktechpost.com/2026/10/09/meet-the-underdog-saluki-27b-a-2-bit-qwen3-8-27b-that-beats-the-original-at-tool-calling/) – MarkTechPost, 2026-10-09

Last updated: 2026-10-09