Unverified50% confidenceBenchmarkExact time
On the uploader's RTX Pro 5000 platform, the speed performance of each model on Xtier is: Qwen 3.8 is the fastest with essentially no waste; DeepSeek 5.3 is slightly slower by 2% than the revised LS济浪; GLM 5.3 is faster than LS济浪; MiniMax M3.1 Flash is very slow.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/25/2026
First Seen
Valid until: 11/8/2026
Sources
Related Entities
Related Claims
UnverifiedUnder Strata 0.2.4, DeepSeek V4.1 Flash generates at about 5 tok/s on an RTX 5070, while an RTX 3060 instead reaches 8 to 10 tok/s.76% similarUnverifiedMiMo V2.6 Flash has 310B total parameters and 15B activated parameters, with a speed nearly twice that of Pro.71% similarUnverifiedA Bilibili uploader used llama.cpp to load the 1-bit quantized version of GLM 5.3 Flash on 4 RTX 3090s, achieving a generation speed of 33.5 tok/s.70% similarUnverifiedThe M5 Ultra's memory capacity is more than five times that of the RTX Pro 6000, but its memory bandwidth is only about two-thirds of the latter.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095842API
curl https://kongchang.com/api/v1/knowledge/claims/1095842MCP
get_claim(id=1095842)