Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
alphaBell
Team
company
https://alphabell.com
alphaBellAI
alphabell-research
Activity Feed
Follow
3
AI & ML interests
Post-training, model behavior and transparent evaluation. Research from alphaBell.
Recent Activity
alphabell-research
new
activity
about 2 hours ago
alphabell/AI-by-the-Numbers:
Show sixteen routed experts working in a smaller latent space
alphabell-research
new
activity
about 14 hours ago
alphabell/AI-by-the-Numbers:
Show a learning rate that stays flat while checkpoints merge
alphabell-research
new
activity
1 day ago
alphabell/AI-by-the-Numbers:
Show why a prefix cache turns ten reads into one
View all activity
Articles
Ling 3.1 Flash 1019: same setup, new weight shards
22 days ago
Draw a MOSS layout once, then run it in ComfyUI
22 days ago
52 full-attention layers versus 16: mapping Nanbeige and Qwen
23 days ago
Five experiments inside Flint and Qwen Open
26 days ago
Draw MOSS-Image layouts without doing coordinate arithmetic
26 days ago
Three tiny bugs that broke Flint's games
26 days ago
alphaBell Qwen Open: 27B post-training, with the tradeoffs measured
27 days ago
View all articles
Team members
1
alphabell
's models
3
Sort: Recently updated
alphabell/alphaBell-Qwen3.8-27B-Open-GGUF
Text Generation
•
27B
•
Updated
26 days ago
•
162
alphabell/Flint-Matched-GGUF
Text Generation
•
40B
•
Updated
26 days ago
•
178
alphabell/alphaBell-Qwen3.8-27B-Open-FP8
Image-Text-to-Text
•
28B
•
Updated
27 days ago
•
127