Unverified50% confidenceBenchmarkExact time
arXiv's SpecDec-Hybrid paper reports a 2.3x wall-clock speedup on a 4-GPU node, reducing latency for 2k-token long-form generation from 12 seconds to about 5 seconds.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn an 8GB GPU, the token generation speed is approximately 4.2 to 5 tokens/second, and decreases from around 6 tokens/second to approximately 4.2 as the context grows longer.77% similarUnverifiedTwo additional single runs were done to separate the variables: dropping agy's model to gemini-3.8-flash-low still took 332 seconds and 67 tool calls; switching to claude-opus-5-5-high, agy used only 51 seconds and 7 tool calls, close to Claude Code's 29 seconds.73% similarUnverifiedPerplexity published self-tested latency (September 30): under 2 seconds for a few hundred input tokens, about 5 seconds for 90k tokens, about 14 seconds for 190k tokens, and about 23 seconds near the 262k limit.72% similarUnverifiedThe Neon checkpoint mechanism takes approximately 650 milliseconds to create a branch and approximately 2.9 seconds to roll back to a branch.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054140API
curl https://kongchang.com/api/v1/knowledge/claims/1054140MCP
get_claim(id=1054140)