# 唐杰：确定模型最优规模并不简单，Fable 或仅 2-2.5T 参数

- 来源：jietang (@jietang)
- 发布时间：2026-09-10 10:10
- AIHOT 分数：28
- AIHOT 链接：https://aihot.news/items/cmtuwrfmn0hi4rorp277hfv9p
- 原文链接：https://x.com/jietang/status/2097870259931988235

## AI 摘要

唐杰指出确定模型最优规模并不简单，需权衡数据量、激活参数量、环境数量和目标推理成本，性能还受多种因素影响。其引用讨论称 Fable 约为 2-2.5T 参数而非 10T，Kimi K3 为 2.8T 参数、训练约用 20-30k Blackwell 等效算力，能力接近 Fable 5（非 5.1）。

## 正文

Are you sure? Finding the optimal model size is tricky: data volume, active parameter count, the number of environments, and the target inference cost. Model performance also depends on many other factors, each introducing its own variability.

### 引用推文

> Charlie O'Neill：Fable is probably ~2-2.5T parameters, not 10T. Kimi K3 is 2.8T params, trained on maybe 20–30k Blackwell-equivalents. It lands within spitting distance of Fable...