#rtx3090 — Public Fediverse posts

We got 207 tok/s with Qwen3.5-27B on an RTX 3090

https://github.com/Luce-Org/lucebox-hub

#HackerNews #Qwen3.5 #RTX3090 #tok/s #machinelearning #AIperformance

Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU

https://github.com/xaskasdf/ntransformer

#HackerNews #Llama3.1 #RTX3090 #NVMe #GPU #bypass #CPU #AItechnology

LLM from scratch, part 28 – training a base model from scratch on an RTX 3090

https://www.gilesthomas.com/2025/12/llm-from-scratch-28-training-a-base-model-from-scratch

#HackerNews #LLMfromScratch #RTX3090 #BaseModel #AITraining #MachineLearning

Google Releases Gemma 3 QAT AI Models for Consumer GPUs

#AI #AIModels #GoogleAI #Gemma3 #LLM #OpenSourceAI #GPUs #QAT #Quantization #DeepLearning #MachineLearning #NVIDIA #RTX3090 #Kaggle

https://winbuzzer.com/2025/04/20/google-releases-gemma-3-qat-ai-models-for-consumer-gpus-xcxwbn/

I’m building a high-end #gaming PC. The #CPU is #intel core #i912900k, on #ASUS ROG MAXIMUS HERO motherboard.
But when it comes to the #GPU I have two ideas, either I go with one of #RTX3090 / #RTX3080 Ti / #rx6900xt or wait the new #Nvidia & #AMD series.

It should be built by 2022/2/15.

#radeon #pcbuild #pcbuilder