"Inference Engineering" is now available. Get your copy here

Ali Taha

Model performance

I spent 31 hours on the math behind TurboQuant so you don't have to

Ali Taha
Turboquant
Model performance

Four Bits: 4-Bit Quantization for Inference Optimization in FLUX.2 [dev]

Ali Taha
four bits

Explore Baseten today

Start deployingTalk to an engineer
Ali Taha