Unverified50% confidenceBenchmarkExact time
MacStories measured GLM 5.3 Flash generation speed at between 31 and 41 tokens per second on its 256GB review machine.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/14/2026
First Seen
Valid until: 2/12/2027
Sources
Related Entities
Related Claims
VerifiedM3.1 Flash's output speed reaches 200+ tokens per second.74% similarUnverifiedZhipu has released GLM-4.5 FlashX, reaching a maximum speed of 200 tokens/second, with the API now live.74% similarUnverifiedLing 3.0 Tiny achieves an inference speed of approximately 86–90 tokens per second on a MacBook with M4 Pro, with a peak memory usage of approximately 8.34 GiB under an 8K context.73% similarUnverifiedIn 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.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1169144API
curl https://kongchang.com/api/v1/knowledge/claims/1169144MCP
get_claim(id=1169144)