# Poolside Laguna S 2.1：本地最强编程模型

- 来源：Thomas Wolf (@Thom_Wolf)
- 发布时间：2026-07-22 16:46
- AIHOT 分数：49
- AIHOT 链接：https://aihot.virxact.com/items/cmry2wovt00hsroqazgz4392d
- 原文链接：https://x.com/Thom_Wolf/status/2079850643188044107

## AI 摘要

Hugging Face 联创 Thomas Wolf 推荐关注 poolside，称其 Laguna S 2.1 是目前可在本地（单台 DGX 或 Mac）运行的最佳编程模型。该模型在 Terminal-Bench 2.1 上得分 70.2，超越部分 5-25 倍参数规模的模型；在 DeepSWE 基准上得分 40.4，优于一些超 1T 参数的开源模型。

## 正文

You should probably go give @poolsideai a follow on Hugging Face.

These folks are on a roll, releasing one agentic coding models every month and the latest one Laguna S2.1 is quite possibly the best coding model you can run locally (single DGX spark or Mac) atm

### 引用推文

> Poolside：Laguna S 2.1 is, as far as we can measure, the most capable agentic coding model in its weight class. On Terminal-Bench 2.1 it scores 70.2, sitting beside model...