Unverified50% confidenceFactExact time
The research team fine-tuned ten open-source models using LoRA, with parameter sizes ranging from under one billion to several billion.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
Unverified开发团队用分布式拆层方法测试过高达1万亿参数的模型75% similarVerifiedThe GPU resources required for a single inference of a hundred-billion-parameter flagship model may be 10 to 20 times higher than those of a ten-billion-parameter model.74% similarUnverifiedA model with 100 billion parameters requires approximately 80 GB of VRAM to process a single inference request, while a model with tens of billions of parameters requires only about 20 GB.72% similarUnverifiedA study on the Spanish MIR residency exam used four open-source models with 800 million to 27 billion parameters, grading 1,552 questions across eight sittings according to the exam's own rules.71% similarUnverifiedThe research team evaluated more than ten representative models.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129074API
curl https://kongchang.com/api/v1/knowledge/claims/1129074MCP
get_claim(id=1129074)