Hoping for Optimized Smarter Upcoming Models .... Like DeepSeek-V4.1-Flash( KVCache + Engram) in Small/Medium/Big sizes
英文标题：Hoping for Optimized Smarter Upcoming Models .... Like DeepSeek-V4.1-Flash( KVCache + Engram) in Small/Medium/Big sizes
It's still a dream for many folks to run medium size(30B range) models @ Q8 with Unquantized KVCache (256K Context) on their GPUs. It would be awesome to have DeepSeek-V4.1-Flash's KVCache + Engram for all Upcoming models. Even for big models. Engram - Heard that approximately 1/3-1/2 of Model
打开原文相关 2 · 机会 0
中文
It's still a dream for many folks to run medium size(30B range) models @ Q8 with Unquantized KVCache (256K Context) on their GPUs. It would be awesome to have DeepSeek-V4.1-Flash's KVCache + Engram for all Upcoming models. Even for big models. Engram - Heard that approximately 1/3-1/2 of Model
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
It's still a dream for many folks to run medium size(30B range) models @ Q8 with Unquantized KVCache (256K Context) on their GPUs. It would be awesome to have DeepSeek-V4.1-Flash's KVCache + Engram for all Upcoming models. Even for big models. Engram - Heard that approximately 1/3-1/2 of Model