Unverified50% confidenceFactExact time
Decision Models use the laya model under the hood, which is 449 MB in size and licensed under Apache-2.0.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Related Entities
Related Claims
UnverifiedLaya uses the Apache 2.0 license, is fully self-hostable (laya-serve), and also has a free Demo Space; it consists of ModernBERT-large 421M and mmBERT-base 322M encoders and can run on a T4 or even a CPU, with CPU latency of 193–464ms.62% similarUnverifiedCurrently, Decision Models only support local operation, and the 449 MB model size may still be a burden for resource-constrained environments.62% similarUnverifiedA 125-billion-parameter model can run on 12G of VRAM, relying mainly on model quantization and a mixture-of-experts (MoE) architecture, achieved by activating only part of the expert parameters, quantizing weights to 4bit or lower, and dynamically loading inactive parameters from memory or SSD on demand.59% similarUnverifiedThe tool uses a local small model for transcription, available in two versions of 142 MB or 466 MB.58% similarUnverifiedFor a very large MoE model such as 816B, even if only 42B parameters are activated, the original weights still need to reside fully in memory, so quantization is almost a prerequisite for running it on consumer-grade hardware.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112294API
curl https://kongchang.com/api/v1/knowledge/claims/1112294MCP
get_claim(id=1112294)