GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
long10024070
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
long10024070
Model Tree
amd/GLM-5.2-MXFP4
Input Modalities
Output Modalities
Supported Functionality
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.