long10024070

GLM-5.2-HYBRID-FP8-MXFP4

README

License: mit

GLM-5.2 Hybrid FP8/MXFP4

This deterministic checkpoint uses block-FP8 non-MoE weights and the block-FP8 MTP layer 78 from zai-org/GLM-5.2-FP8. Routed and shared MoE expert tensors for layers 3 through 77 are copied byte-for-byte from amd/GLM-5.2-MXFP4. No tensor is dequantized or requantized during assembly.

The checkpoint declares hybrid-fp8-mxfp4 and requires the matching conditional SGLang loader patch shipped with its reproducibility assets. Original FP8 and Quark checkpoints do not use that patch path.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

long10024070

Model Tree

Base