Jundot/DeepSeek-V4.1-Flash-oQ3e-mtp
Designed by OMLX PR#3574 and Astra/implemented by Opus5 M3 Ultra 512GB over 260K (300GB over) Real time about 20tok/s Model release/quantization/PR/oMLX Thank you to everyone
limegreenpeper753Sep 11
A service has been released that allows you to use AI models from various companies at a low price, with over 20 million imps being sold overseas.
You can use it at up to 81% cheaper, and you can also choose a setting that does not leave data (ZDR). ・You can use models from multiple companies with one API (remains in the same format as before) ・More than 66 models (OpenAI, Anthropic, DeepSeek, etc.)
Made an ocean simulation with Deepseek V4.1 Flash.
DeepSeek thinking is too fast, about 3 times the GLM experience
You have reached the end of the archive
All of deepseek