GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
OpenYourMind
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OpenYourMind
Model Tree
zai-org/GLM-5.3-Flash
Input Modalities
Output Modalities
Supported Functionality
Glm5NextForConditionalGeneration (glm5_next), multimodal (image-text-to-text)nvfp4-pack-quantized, group size 16bash
vllm serve OpenYourMind/GLM-5.3-Flash-NVFP4-sel3-MTP \ --trust-remote-code \ --tensor-parallel-size 4 \ --tool-call-parser glm47 \ --enable-auto-tool-choice \ --reasoning-parser glm45 \ --enable-prefix-caching \ --speculative-config '{"method":"mtp","num_speculative_tokens":1}'Drop the --speculative-config line to run without speculative decoding.
Requires an NVFP4-capable GPU (Blackwell / sm100+) for the native FP4 path.
Derived from zai-org/GLM-5.3-Flash (MIT).