Bolt has published the first 48 hours of usage data from Bolt Forge.
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
Bolt has published the first 48 hours of usage data from Bolt Forge. > Forge is a mode inside the Bolt AI app builder, which allows users to run open-source models. > The full split was GLM 5.3 Flash at 46%, DeepSeek V4 Pro at 21%, GLM 5.3 at 17%, and Kimi K3 at 16%. These results show GLM 5.3 Flash, the fastest and cheapest of its four models, taking the largest share of prompts and, on average, receiving prompts twice the size of the rest.
Posted by 🚨 AI News | TestingCatalog (76k followers) 1 days ago · 83 likes · 12.1k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: Bolt Lite.
More dev work like this
- Hallmark has been installed 50k+ times! — @nutlope
- Your AI coding agents need a workflow, not more babysitting. — @DanKornas
- Register by October 7 and save >> https://bit.ly/4vkntyD — @linuxfoundation
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.