English(EN) Gemma-4-31B-it-Pearl supports 32K context, configurable thinking, function calling, and JSON mode.

Together AI 发布 Pearl 驱动的 Gemma-4-31B-it-Pearl 模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-16 01:46

Together AI 发布了 Gemma-4-31B-it-Pearl，这是一个具有增强功能的开源模型。该模型支持 32K 上下文窗口、可配置的思考过程、函数调用和 JSON 模式。这是 Together AI 首次推出由 Pearl 驱动的产品，并计划未来扩展其基于 Pearl 的产品线。 AI

影响为开发者提供了一个具有扩展上下文窗口和函数调用等高级功能的新型开源模型。

排序理由非前沿实验室发布的开源模型。[lever_c_demoted from research: ic=1 ai=1.0]

在 X — Together (inference / OSS) 阅读 →

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

Together AI 发布 Pearl 驱动的 Gemma-4-31B-it-Pearl 模型

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; 非前沿实验室发布的开源模型。[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: 114 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]

X — Together (inference / OSS) TIER_1 English(EN) · togethercompute · 2026-05-16 01:46

Gemma-4-31B-it-Pearl 支持 32K 上下文、可配置思考、函数调用和 JSON 模式。

Gemma-4-31B-it-Pearl supports 32K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to expand our Pearl powered product portfolio, and offer ways for customers to directly obtain a

本文如何被排名

报道来源 [1]

Gemma-4-31B-it-Pearl 支持 32K 上下文、可配置思考、函数调用和 JSON 模式。

相关实体

相关话题