Partially Verified65% confidenceBenchmarkExact time
On a dual-Spark system, DeepSeek V4 Flash (FP8 quantization) peaks at approximately 53 tokens per second.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 Flash is a cloud-based model focused on high throughput, with an inference speed of approximately 140 tokens per second.79% similarUnverifiedUnder 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.75% similarUnverifiedOn a dual-Spark system, GLM 5.3 Flash peaks at approximately 46 tokens per second.75% similarUnverified盘古2.0 Flash在LiveCodeBench算法推理测试中得分85.1，仅次于DeepSeek V4 Flash的91.6，超过千问3.6 27B的83.974% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/896147API
curl https://kongchang.com/api/v1/knowledge/claims/896147MCP
get_claim(id=896147)