Peasant Smith (@PeasantSmith)

2026.10.11 19:11

GLM 5.3 Flash on a single 3090 at 24.3 t/s decode and over 1000t/s prefill 🔥 And yes, prefill has been optimised and it does get faster the bigger the context window, not magic, just hard work on Maya engine 🫡

Forward to community

Peasant Smith@PeasantSmith

2026.10.11 13:37

Maya is on 🔥 57k downloads and growing! Thank you all for trying and sharing the models and engine I hope you are having fun 🫡

Forward to community

Peasant Smith@PeasantSmith

2026.10.10 20:39

a single 3090, a single 3090, a single 3090, a single 3090, a single 3090 320B parameters, 320B parameters, 320B parameters, 320B parameters 18B active, 18B active, 18B active, 18B active, 18B active, 18B active, 18B active Project Maya 💎

Forward to community

Peasant Smith@PeasantSmith

2026.10.05 23:03

I know Niko's been busy, but I'm kind of impatient This is one day of me with Claude Pro (cheapest plan) access😂 🔥GLM 5.3 Flash ⚖️93.1GB model file (the smallest, for now) 👍About 20t/s decode ⚒️Fully custom version of Strata 😥No MTP (yet) 🐌Xeon E5 2690 V4 🐌32GB ddr4 quad channel 🐌NVME 3.0 ⭐2x Tesla V100 PCIe 32GB I have redated part of the dashboard numbers because it is all new and I don't want to spoil anything until that is ready. I left the experts location open though, in case anyone thinks that is not the model I claim :) I enjoyed working on it, so I plan to carry on with optimisations and eventually release it all, stay tuned! More to come⏳