PulseAugur
EN
LIVE 03:21:06

llama.cpp adds Gemma4 tool call support in latest release

By PulseAugur Editorial · [1 sources] ·

The llama.cpp project has released version b12388, which introduces support for tool calls with the Gemma4 model. This update allows Gemma4 to make tool calls directly from its thought process without needing to close the thought channel first. The change aims to improve the model's ability to interact with external tools. AI

IMPACT Enables more direct tool interaction for Gemma4 within the llama.cpp framework.

RANK_REASON This is a software release for a specific project (llama.cpp) that enables a feature for a particular model (Gemma4), rather than a core AI model release or significant industry event.

Read on llama.cpp — Releases →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

llama.cpp adds Gemma4 tool call support in latest release

How we ranked this

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a software release for a specific project (llama.cpp) that enables a feature for a particular model (Gemma4), rather than a core AI model release or significant industry event.
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
product, model release
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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. llama.cpp — Releases TIER_1 English(EN) · cristianadam ·

    b12388: chat : allow Gemma4 tool call during thought (#32232)

    <p>The thought channel is normally closed with &lt;channel|&gt;, but the model<br /> may open it and go straight to a tool call without closing it. Stop the<br /> reasoning at &lt;channel|&gt; OR &lt;|tool_call&gt;, so an unclosed thought does<br /> not swallow the following tool…

RELATED ENTITIES

RELATED TOPICS