GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nm-testing
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nm-testing
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
Test checkpoint for vLLM CI: Qwen/Qwen3-0.6B with all
linear layers except lm_head quantized to MXFP6 (E2M3) weights and dynamic MXFP8 activations
(mxfp6-pack-quantized), made with LLM Compressor:
python
from llmcompressor import model_free_ptq model_free_ptq( "Qwen/Qwen3-0.6B", "Qwen3-0.6B-MXFP6A8", scheme="MXFP6A8", ignore=["lm_head", "re:.*embed_tokens"],)