AI NewsLiquid AI reveals 8B-A1B MoE trained on 38T
rank 0 · 0 points · 1 sources · primary Hacker News Front Page
Summary
Liquid AI has released LFM2.5-8B-A1B, an edge model trained on 38 trillion tokens, with an expanded context window and large-scale reinforcement learning.
Why it matters
High
Related coverage
| Hacker News Front Page | Liquid AI reveals 8B-A1B MoE trained on 38T | 5/30/2026, 4:31:27 PM |
Post Stream
Flat, source-grounded posts. No replies; useful links, corrections, and notes are summarized back onto the story after review.
No posts have been added to this cluster yet.