---
id: "entity-gemini-d49"
type: "entity"
entityType: "product"
canonicalName: "Gemini"
aliases: ["Google Gemini"]
source_timestamps: ["14:04:00"]
tags: ["product", "llm"]
related: ["entity-google", "claim-google-compounding-advantage"]
canonicalUrl: "https://deepmind.google/technologies/gemini/"
sources: ["s49-killed-ram-limits"]
sourceVaultSlug: "s49-killed-ram-limits"
originDay: 49
---
# Gemini

Gemini is [[entity-google-d49]]'s flagship suite of multimodal foundation models.

**Why it matters in this vault**: Google has explicitly stated that the [[concept-kv-cache]] is a bottleneck for Gemini, making it the **prime target** for [[concept-turboquant]] implementation.

The combination of:
- Gemini as the deployment target,
- TPU as the hardware substrate,
- Turboquant as the compression algorithm,

is what enables the compounding cost advantage argued in [[claim-google-compounding-advantage]].

**Canonical URL**: https://deepmind.google/technologies/gemini/