You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/on-device-ai-goes-mainstream.mdx
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -76,7 +76,7 @@ Large foundation models (LLMs) remain costly and centralized. In contrast, [**Sm
76
76
This makes them ideal for **local AI** scenarios: assistants, semantic search, or multimodal apps running directly on-device. However....
77
77
78
78
### Frontier AI Models are still getting bigger and costs are skyrocketing
79
-
<imgsrc="/img/edge-ai/slm-quality-cost.png"alt="SLM quality and cost comparison" />
79
+
<imgsrc="/img/edge-ai/llm-costs-still-skyrocketing.png"alt="SLM quality and cost comparison" />
80
80
81
81
### Why this matters for developers: Monetary and hidden costs of using Cloud AI
82
82
@@ -87,15 +87,15 @@ Running cloud AI comes at a cost:
87
87
-**Dependency**: Few tech giants hold all major AI models, the data, and the know-how, and they make the rules (e.g. thin AI layers on top of huge cloud AI models will fade away due to vertical integration)
88
88
-**Data privacy & compliance**: Sending data around adds risk, sharing data too (what are you agreeing to?)
89
89
-**Sustainability**: Large models consume waqy more energy, and transmitting data unnecessarily consumes way more energy too (think of this as shopping apples from New Zealand in Germany) ([Sustainable Future with Edge Computing](https://objectbox.io/why-do-we-need-edge-computing-for-a-sustainable-future/)).
90
-
<imgsrc="/img/edge-ai/slm-quality-cost.png"alt="SLM quality and cost comparison" />
90
+
<imgsrc="/img/edge-ai/why-llm-costs-and-energy-consumption-impacts-developers.png"alt="SLM quality and cost comparison" />
91
91
92
92
### What about Open Source AI Models?
93
93
94
94
Yes, they are an option, but be mindful of potential risks and caveats. Be aware that you also pay to be free of liability risks.
95
-
<imgsrc="/img/edge-ai/slm-quality-cost.png"alt="SLM quality and cost comparison" />
95
+
<imgsrc="/img/edge-ai/opensource-ai-models.png"alt="SLM quality and cost comparison" />
96
96
97
97
### While SLM are all the rage, it's really about specialised AI models in Edge AI (at this moment...)
98
-
<imgsrc="/img/edge-ai/slm-quality-cost.png"alt="SLM quality and cost comparison" />
98
+
<imgsrc="/img/edge-ai/for-mobile-it-is-specialized-models-not-SLM.png"alt="SLM quality and cost comparison" />
99
99
100
100
101
101
## On-device Vector Databases are the second essential piece of the Edge AI Tech Stack
0 commit comments