Kindling AI 发布 exlr8 K2/K3/K4 量化版本，面向 744B MoE 模型 GLM-5.3，用于多节点本地部署。提供 219GB 至 378GB 的灵活内存配置，K2/K3/K4 专家权重随同一份权重集一起提供，可在加载时切换精度，无需重新编码。该版本为预览版，面向 3–7 个统一内存节点的张量并行设计，已测试 TP=3 和 TP=4。
Full GLM-5.3, compressed for multi-node local serving. Kindling AI releases an exlr8 K2/K3/K4 quantization of the 744B MoE model.
🤖 https://modelscope.ai/models/kindlingai/glm-5.3-exlr8-k2-k3-k4
📦 Flexible memory targets: Choose profiles ranging from 219GB to 378GB, depending on the quality and memory budget of the deployment.
⚙️ One weight set, multiple precisions: K2, K3, and K4 expert weights ship together, letting users change the precision mix at load time without re-encoding the model.
🖥️ Built for distributed local inference: Designed for tensor parallelism across 3–7 unified-memory nodes, with TP=3 and TP=4 configurations already tested.
🧪 Quality-aware allocation: Hessian-calibrated manifests spend additional bits where they reduce divergence from the original BF16 model most effectively.
📌 Preview release. Performance and full BF16-alignment validation are still in progress. GLM-5.3 License applies.
来源：ModelScope · x.com