Unverified50% confidenceFactExact time
L402 is the oldest of the four protocols (originating in 2020), with the smallest GitHub metrics: 91 stars, 8 contributors, zero commits in 90 days, and there is a fork problem—another repository with more stars (l402-protocol/l402, 227 stars) claims to be the new continuation of the same specification.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedThe smallest model, LFM 1.2B, has a median generation rate of approximately 208 tokens/s, with a current task score of only 5/16 substantive and 2/16 strict.57% similarUnverifiedLFM2.5-24B-A2B uses a 40-layer architecture: 30 double-gated short convolution blocks + 10 GQA attention layers, 64 experts per MoE block, top-4 routing, a 131,072 token context, and a 128K vocabulary.57% similarUnverifiedThis release involves commit records 16a04d7 and 29dc427.56% similarUnverifiedL40S是NVIDIA面向数据中心推出的专业计算卡，配备48GB GDDR6显存55% similarUnverifiedThe A100 (2020) delivers 312 TFLOPS of FP16 compute and 2 TB/s of HBM2e bandwidth; the H100 (2022) increases FP16 compute to 989 TFLOPS and introduces FP8 support for the first time; the B200 (2024) pushes FP8 compute to the 9 PETAFLOPS level with HBM3e bandwidth reaching 8 TB/s.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036387API
curl https://kongchang.com/api/v1/knowledge/claims/1036387MCP
get_claim(id=1036387)