Raghav agarwal

icon location India icon location Aspiring Machine Learning engineer, currently exploring deep learning, transformers, and deploying models at scale.

Results 2 comments of Raghav agarwal

Running FLUX inference twice gets slower on second run.

The slowdown happens because macOS’s unified memory system begins swapping parts of the FLUX model’s memory to disk after the first run on 64 GB machines. The model (~31 GB)...

[BUG] Claude Code, Anthropic API, unable to send images

The issue occurs because the Anthropic API currently does not support the image variant in the messages[].content field.