284B
PulseAugur coverage of 284B — every cluster mentioning 284B across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
DeepSeek-V4-Flash 284B model runs on 64GB RAM via llama.cpp patches
A new set of patches for llama.cpp, a popular open-source tool for running large language models locally, enables the 284B parameter DeepSeek-V4-Flash model to run on systems with only 64GB of RAM. The repository, llama…
-
New 'grafting' technique efficiently modifies LLM beliefs across checkpoints
Researchers have developed a new technique called "grafting" to more efficiently modify the beliefs of large language models during their training process. This method addresses the costly and time-consuming nature of t…
-
DeepSeek V4 release forces 80% price cut from competitor
A company was forced to reduce its prices by 80% due to the competitive pressure from DeepSeek V4. This new open-source model, featuring 284 billion parameters and 13 billion active parameters, offers superior price-to-…