Unverified50% confidenceOpinionExact time
The 31M parameter scale is roughly only one percent of mainstream cloud TTS models.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
Unverified本地可运行的模型如 Llama 3 8B、Qwen2 7B 参数仅为顶级云端模型的约百分之一68% similarUnverifiedReflection-Beam-1.0 has a total parameter scale of 501B, with only 23B parameters activated per inference.65% similarUnverifiedThe blogger estimates that a single Front Matter occupies approximately only 25 tokens.63% similarUnverified万象模型提供了 1.3B 和 14B 参数量的不同规模版本62% similarUnverifiedBeam's VRAM requirement is close to that of a 501B-scale model, while its compute requirement is close to that of a 23B-scale model.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1086611API
curl https://kongchang.com/api/v1/knowledge/claims/1086611MCP
get_claim(id=1086611)