PulseAugur
中
实时 04:27:04
English(EN) Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling

Underdog发布2位量化Saluki 27B模型,在工具调用方面超越Qwen3.8-27B

Underdog(Conway Research的研究项目)发布了Saluki 27B,这是Qwen3.8-27B模型高度压缩的2位量化版本。这款新模型采用Apache 2.0许可证发布,文件大小从54 GB显著减小到7.89 GB,使其能够在标准的llama.cpp实现上运行。虽然Saluki 27B在工具调用方面表现出性能提升,保留率达到原始模型的120%,但在复杂推理和数学任务方面性能有所下降。 AI

影响 通过显著减小模型尺寸并保持工具调用等关键功能,实现了更强大的设备端智能体。

排序理由 发布量化模型并进行性能比较。[lever_c_demoted from research: ic=1 ai=1.0]

在 MarkTechPost 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Underdog发布2位量化Saluki 27B模型,在工具调用方面超越Qwen3.8-27B

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
发布量化模型并进行性能比较。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
5 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. MarkTechPost TIER_1 English(EN) · Michal Sutter ·

    认识一下黑马 Saluki 27B:一款击败原版的 2-bit Qwen3.8-27B 工具调用模型

    <p>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.</p> <p>The post <a href="https://www.marktechpost.com/2026/10/09/meet-the-underdog-saluki-27b-a-2-bi…