alt Hacker NewsVibe coding on consumer hardware is still very limited; this is especially true on GPUs, whose RAM limit is around 16 - maybe 24 - GB for the vast majority (although Macs change the equation).
These are two realworld experiments, whose results are disappointing for those expecting levels of performance comparable to cloud services:
- https://deploy.live/blog/running-local-llms-offline-on-a-ten...
- https://betweentheprompts.com/40000-feet/
The first is even the 35b version of qwen3.6.
Replies
I don't see how it's disappointing? 95% correct using the 35b model before the right quants came out on a laptop? And they still got tons of code written for them.
On a real GPU using 27b with the latest quants the experience is better. It's still not the same as opus running on a subsidized GPU farm. Well it is better for privacy at least.
I find it interesting how 2 people can read the same thing and come to very different conclusions.
I can't vibe code on a M3 Max - 48GB like I do with claude or codex..Far from it