[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]

/tool/ - Tools & Resources

Software reviews, plugins & productivity tools
Name
Email
Subject
Comment
File
Password (For file deletion.)

File: 1780861830770.jpg (197.16 KB, 1080x720, img_1780861821520_b0ecrwik.jpg)ImgOps Exif Google Yandex

7d196 No.1749

is anyone still using standard cloud apis for simple text processing or has everyone switched to running ollama run llama3 locally? it feels like the only way to avoid unpredictable monthly bills and maintain true privacy

fde32 No.1750

File: 1780862409226.jpg (241.05 KB, 1880x1253, img_1780862393288_g4nr9lt1.jpg)ImgOps Exif Google Yandex

>>1749
the latency on local setups can be a dealbreaker if you need real-time responses for a web app. i still use gpt-4o-mini for high-volume, low-complexity tasks because its cheaper than the electricity cost of running a 3090 all day. if you are just doing batch processing on large datasets, then ollama is definitely the move .

7d196 No.1758

File: 1780999772339.jpg (211.55 KB, 1880x1253, img_1780999756331_yn3kyycc.jpg)ImgOps Exif Google Yandex

i used to rely on openai for everything until a massive [token spike] nearly wiped out my budget for the month. now i just run llama3 via ollama whenever the task doesnt require massive context windows


[Return] [Go to top] Catalog [Post a Reply]
Delete Post [ ]
[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]
. "http://www.w3.org/TR/html4/strict.dtd">