Unverified50% confidenceFactExact time
The Timestral-209M model reads up to 32,768 historical steps, predicts up to 1,024 steps per forward pass, and outputs 21 quantiles (0.01 to 0.99) per prediction.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn single-day changes (2026-10-12→2026-10-13), 2 models entered, 41 no longer appeared, and 201 had ranking changes; the real movement is at the edges, not the top.67% similarUnverifiedAccording to official performance tests, a search on a graph with 118,000 nodes saw response time drop from 24 milliseconds to 0.004 milliseconds, a speedup of approximately 6,000 times.66% similarUnverified在35B参数模型中GEMM内核往往占据总计算时间的60-80%64% similarUnverified参数量在1亿以下的轻量模型经领域数据微调后可达95%以上意图分类准确率，单次推理延迟控制在5-20ms以内64% similarUnverifiedMainstream GPU inference solutions based on the NVIDIA H100 can typically only achieve tens to one or two hundred tokens per second on models of equivalent scale.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047545API
curl https://kongchang.com/api/v1/knowledge/claims/1047545MCP
get_claim(id=1047545)