#Ternary-Bonsai discussion
on 02026-04-24oh, you can run #LLMs like #Ternary-Bonsai on #WebGPU. It, uh, takes quite a while to load tho. In fact I think it’s hung.
on 02026-04-22"Ternary Bonsai" is a quantization of Qwen3-8B to 1.58-bit weights {-1, 0, +1}, I think like the original BitNet. Quite competent at conversation, and fast, but sort of dumb. #neural-networks #AI #LLMs
on 02026-04-22