cd/entity/DeepSeek-V4 Flash 284B-A13B· home› entities› DeepSeek-V4 Flash 284B-A13B

grep -l @deepseek-v4 flash 284b-a13b /news/*.json | wc -l → 1

DeepSeek-V4 Flash 284B-A13B

mentions 1 type Person feed RSS

// recent coverage 1 mentions

08:45

2026-09-21

dev.to

large-language-models

Yandex open-sourced an 80B model trained from scratch: what's inside and where it wins

Yandex released AliceAI-Foundation-80B-A3B-Base, an 80B-parameter mixture-of-experts language model trained entirely from scratch on roughly 18T tokens and published on Hugging Face under Apache 2.0. …

// co-occurs with top 7 entities

Yandex 1 AliceAI-Foundation-80B-A3B-Base 1 Hugging Face 1 Qwen3.5 35B-A3B 1 Nemotron-3 Super 120B-A12B 1 Alice AI 1 Kimi Delta Attention 1

// topics top 5 topics

large language models 1 artificial intelligence 1 ai research 1 ai products 1 natural language processing 1