Unverified50% confidenceBenchmarkExact time
Under a standard synthetic workload of 1k prompt / 512 completion, V4.1 Flash 1017 has a TTFT of 185 milliseconds, total throughput of 480 tokens/s, and KV cache efficiency of 0.65x memory.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/19/2026
First Seen
Valid until: 11/2/2026
Sources
Related Entities
Related Claims
UnverifiedIn a 3D city generator test, V4.1 Flash achieved an output speed of 287 tokens per second, with a total completion time of 83 minutes.77% similarUnverifiedCompared with standard MoE models of the same class, V4.1 Flash 1017 improves TTFT by about 23%, total throughput by about 55%, and KV cache capacity by 35%.76% similarUnverifiedThe community measured V4.1 Flash reaching a peak speed of 400 tokens/second, with little change in speed even when the context is extended to 1 million tokens.76% similarPartially VerifiedOn a dual-Spark system, DeepSeek V4 Flash (FP8 quantization) peaks at approximately 53 tokens per second.75% similarUnverifiedThrough request-owned speculative KV, in a DeepSeek-V4-Pro 1P1D, MI355X, concurrency-256 scenario, the average TTFT was reduced from 19.4 seconds to 15.1 seconds.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067166API
curl https://kongchang.com/api/v1/knowledge/claims/1067166MCP
get_claim(id=1067166)