@hn_4bc5e5
4 months ago
Public discussion, not a rating submitted on Rate My AI.
The old Kimi K2 is better than GLM4.7
1T/32B-active MoE with 256K context and MLA attention, Modified MIT license; 384-expert (8/token) agentic-focused foundation model from Moonshot.
Specific experiences are worth more than sweeping claims.
@hn_4bc5e5
4 months ago
Public discussion, not a rating submitted on Rate My AI.
The old Kimi K2 is better than GLM4.7