alphaBell

company

https://alphabell.com

alphabell-research

AI & ML interests

Post-training, model behavior and transparent evaluation. Research from alphaBell.

Recent Activity

alphabell-research new activity about 4 hours ago

alphabell/AI-by-the-Numbers:Add ECHO final-layer drafting animation

alphabell-research new activity about 16 hours ago

alphabell/AI-by-the-Numbers:Add StateBench state-tracking animation

alphabell-research new activity 1 day ago

alphabell/AI-by-the-Numbers:Enable direct video and poster downloads

View all activity

Articles

Ling 3.1 Flash 1019: same setup, new weight shards

Draw a MOSS layout once, then run it in ComfyUI

52 full-attention layers versus 16: mapping Nanbeige and Qwen

Five experiments inside Flint and Qwen Open

Draw MOSS-Image layouts without doing coordinate arithmetic

Three tiny bugs that broke Flint's games

alphaBell Qwen Open: 27B post-training, with the tradeoffs measured

View all articles

alphabell 's models 3

alphabell/alphaBell-Qwen3.8-27B-Open-GGUF

Text Generation • 27B • Updated 14 days ago • 137

alphabell/Flint-Matched-GGUF

Text Generation • 40B • Updated 14 days ago • 131

alphabell/alphaBell-Qwen3.8-27B-Open-FP8

Image-Text-to-Text • 28B • Updated 15 days ago • 102