#open-weight

Follow to get notified about new posts with this tag

popularai

4d

K2 Horizon 36B-A4B for local AI: what the 4B-active model actually needs

K2 Horizon 36B-A4B for local AI: what the 4B-active model actually needs

K2 Horizon 36B-A4B packs 36B parameters while activating only 4B per token. That sounds perfect for local AI. The catch is what it takes to run well on real hardware. Read the full article on Popular AI

$ 0.000

0

popularai

23d

GLM-5.3 weights are still on hold. Should you wait or use GLM-5.2?

GLM-5.3 weights are still on hold. Should you wait or use GLM-5.2?

GLM-5.3 looks stronger at coding, but its weights are still missing. Should local AI users wait, keep GLM-5.2, or buy hardware now? One key question remains unanswered. Read the full article on Popular

$ 0.000

0

popularai

1M

Meta Muse Glimmer: what one GPU really means for local AI

Meta Muse Glimmer: what one GPU really means for local AI

Meta Muse Glimmer puts a provocative question in front of local AI users: what does “one GPU” actually buy you? The answer comes with a catch. Read the full article on Popular AI

popularai

2M

Can you run Kimi K3 locally? Almost certainly not

Can you run Kimi K3 locally? Almost certainly not

Kimi K3 may be open-weight, but your gaming PC is not invited. Moonshot recommends at least 64 accelerators. So what can local AI users realistically do? Read the full article on Popular AI

shadeflowersart

5d

Addition to family of drawings

Addition to family of drawings

Today was a bit unusual. For the first time, artwork from the ShadeFlowersArt project was freely available for purchase in the real world. It was a fair. And during this fair, some unfinished art was finished.

popularai

2M

Why specialized AI models still beat benchmark kings

Why specialized AI models still beat benchmark kings

AI benchmark leaders look unbeatable. In real workflows, smaller specialized models can still win. The reason exposes what public leaderboards fail to measure. #AI