Simon Willison’s Weblog

Subscribe

20th October 2025

Research deepseek-ocr-nvidia-spark — Successfully deployed DeepSeek-OCR on an NVIDIA GB10 (ARM64, sm_121) by upgrading to PyTorch 2.9.0+cu130 so CUDA 13.0 wheels could be used instead of building from source. The repo includes automated scripts (setup.sh, run_ocr.py) that load the 6.3GB safetensors model (~34s) and run GPU inference (~58s for a 3503×1668 image), producing annotated images, markdown/text outputs and bounding boxes with validated multi-column accuracy.

Recent articles

This is a beat by Simon Willison, posted on 20th October 2025.

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe