Unverified50% confidenceBenchmarkExact time
Ling 3.0 Tiny 每处理一个token的算术运算量约为8B稠密模型的六分之一
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/10/2026
First Seen
Valid until: 11/8/2026
Sources
Related Claims
Unverified蚂蚁集团实验室发布了 Ling 3.0 Tiny 模型，总参数7.9B，每token激活约1.3B72% similarUnverified4-bit量化只能表示16个离散值，1-bit只有2个，三元量化（-1/0/+1）只有3个可能值64% similarUnverified在4-bit量化下，纯参数理论最小占用为：7B约3.26GiB，13B约6.05GiB，32B约14.90GiB，70B约32.60GiB62% similarUnverifiedLing-3.0-flash adopts a Mixture of Experts (MoE) architecture with an activation ratio of only approximately 4% (approximately 5.1B activated out of 124B total parameters).62% similarUnverifiedNex N2 Mini uses approximately 8.6% of its parameters per inference call (3B/35B).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/723989API
curl https://kongchang.com/api/v1/knowledge/claims/723989MCP
get_claim(id=723989)