Unverified50% confidenceBenchmarkExact time
Ziskind tested DeepSeek V4 Flash concurrency: the Mac's total throughput peaked at four users and declined at eight users; with eight users and chat history, each person waited over a minute to first token, after which generation was about 5 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/14/2026
First Seen
Valid until: 2/12/2027
Sources
Related Entities
Related Claims
UnverifiedZiskind tested DeepSeek V4 Flash with a 32,000-token codebase: the 256GB M5 Ultra took about 50 seconds to first token, while two DGX Spark units totaling about $10,000 took only 17 seconds.68% similarUnverifiedMacStories measured GLM 5.3 Flash generation speed at between 31 and 41 tokens per second on its 256GB review machine.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1169145API
curl https://kongchang.com/api/v1/knowledge/claims/1169145MCP
get_claim(id=1169145)