Lotto
@LottoLabs
Building localmaxxing and tinkering
969 Following 12.2K Followers
Tenstorrent p150 support coming as soon as my p150 is free 😉
This is how we’re going to get local models on every computer
Little qwen 27b 3.8 1x3090 vs 2x3090 gguf action
Faster with TP2 on llama which isn’t even tuned for it + mtp
Vllm next + dflash
Does the average Chinese person know they have the best open source models in the world?
