Unverified50% confidenceBenchmarkExact time
Neural 3 reports a decode speed of approximately 400 to 4,000 tokens per second on small development boards.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedAfter writing the KV cache in version V3, the time to generate 100 tokens from a 512-token prompt dropped from 278 seconds to 28 seconds, achieving nearly a 10x inference speedup.68% similarUnverifiedA trained neural network surrogate model can produce approximate results within milliseconds, compressing design iterations that would otherwise take years down to weeks or even days.67% similarUnverifiedPPC中的神经元在动作执行前100至500毫秒就显现出方向性编码活动65% similarUnverifiedOllama在纯CPU上运行时，Token输出速度大约每秒5-10个词65% similarUnverifiedA generation speed of 0.5 tokens/second is comparable to the speed of human thinking output.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977853API
curl https://kongchang.com/api/v1/knowledge/claims/977853MCP
get_claim(id=977853)