Moonshot AI 在 Hugging Face 发布 2.8T 参数的 Kimi K3.1 Pro 模型权重。该模型以 4-bit 精度训练并直接以该精度发布，避免 16-bit 版本所需的 5.6TB 存储；每个 token 仅激活 104B 参数，93 层中有 69 层使用线性注意力，以降低 1M token 上下文的处理成本。
材料把开源权重、4-bit 精度、稀疏激活与许可限制放在一起，便于判断这次发布的开放程度和商用边界。
Moonshot AI released the massive 2.8T-parameter Kimi K3.1 Pro weights on Huggingface.
On Terminal-Bench, its head-to-head with Claude 5.5
Trained with 4-bit weights, it also ships at that precision, avoiding the 5.6TB a 16-bit copy would need.
Moonshot traced steadily rising exploit skill to cyber content buried in its general mid-training corpus and RL environments, and removed both before opening the weights.
In Moonshot’s own tests the model scores 65.7% on Terminal-Bench 4.0, near Claude Opus 5.5’s 66.4%, but without tools reaches only 39.4% on HLE-Diamond, against GPT-6 Astra’s 65.8%.
Only 104B of its parameters fire per token, and 69 of its 93 layers use linear attention, which makes a 1M-token context cheaper to process.
Its modified MIT license exempts internal use but makes model-hosting firms earning over $20M a year negotiate, reining in resellers that could undercut the company’s own API.
Releasing the model weights of Kimi K3.1 Pro: https://huggingface.co/moonshotai/Kimi-K3.1-Pro We'll keep advancing open intelligence.在 X 查看被引用的帖子
来源：Rohan Paul · x.com