Tim Dettmers(@Tim_Dettmers):Fable quality. We will soon release a new quantized inference framework that will let you run this on a single GPU (B300) with ~50 tok/s in good quality. Local Fable LFG!

Tim Dettmers

@Tim_Dettmers

Creator of bitsandbytes. Professor @CarnegieMellon and Research Scientist @allen_ai . I blog about deep learning and PhD life at

加入 October 2012

917 正在關注 48.4K 粉絲

Tim Dettmers@Tim_Dettmers

2026.08.12 19:37

Fable quality. We will soon release a new quantized inference framework that will let you run this on a single GPU (B300) with ~50 tok/s in good quality. Local Fable LFG!

Cline@cline

2026.08.12 18:08

DeepSeek silently released V4-Pro 0813, up 15.8% on Terminal Bench from their April Preview model, with Fable 5 performance at ~57x cheaper cost. 1.6T param, 49B active, 1M context. This is the best price-to-perfomance model on the market right now. Available in ClinePass now!