Unverified50% confidenceFactExact time
Anthropic published a research paper showing that a relatively small 9-billion-parameter model successfully completed AI inference setup on 8 of the 9 hardware types tested, and successfully ran a 26-billion-parameter model on 15 cheap Android TV boxes.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA 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.74% similarUnverifiedOn-device AI can typically only run small quantized models with parameter counts in the range of 1 billion to 7 billion.71% similarUnverifiedApple's on-device model reportedly has 20 billion parameters and uses an MoE-style partial activation mechanism, activating only 1 billion to 4 billion parameters per inference.70% similarUnverifiedAlibaba's new-generation Qianwen model has 2.4 trillion parameters, making it the first multimodal large model in the series to exceed one trillion parameters; its code generation accuracy is reportedly 94.7%, an improvement of approximately 11 percentage points over the previous generation.70% similarUnverified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70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030341API
curl https://kongchang.com/api/v1/knowledge/claims/1030341MCP
get_claim(id=1030341)