GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sasa2000
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
sasa2000
Model Tree
ATH-MaaS/Marco-Nano-Instruct
Input Modalities
Output Modalities
Supported Functionality
0.151988theblackcat102/evol-codealpaca-v1model_max_length: 2048batches_per_category: 128batch_size: 1batch_group_size: 8This checkpoint was created for a low-resource pruning experiment on a 6GB VRAM environment. Benchmark evaluation was not run. A short prompt smoke check showed this ratio to be the most stable of the tested Marco-Nano pruning ratios, especially in English; Japanese and Chinese outputs may still show repetition or wording artifacts.