TNG Technology Consulting GmbH

Team

company

Verified

https://www.tngtech.com/

tngtech

TNG

Activity Feed Request to join this org

AI & ML interests

MoE architectures, Chimera models, Assembly of Experts

Articles

How Long Prompts Block Other Requests - Optimizing LLM Performance

Finetuning olmOCR to be a faithful OCR-Engine

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

Efficient Request Queueing – Optimizing LLM Performance

tngtech 's models 5

tngtech/DeepSeek-TNG-R1T2-Chimera

Text Generation • 685B • Updated Nov 4 • 879 • 263

tngtech/DeepSeek-R1T-Chimera

Text Generation • 685B • Updated Nov 4 • 425 • 265

tngtech/Phi-3-mini-4k-instruct-sym-int4-channelwise-ov

Updated May 23 • 27

tngtech/olmOCR-7B-faithful

Image-to-Text • 8B • Updated May 9 • 41 • 18

tngtech/OLMo-2-Instruct-Math-32B

Text Generation • 32B • Updated Apr 17 • 21 • 7