GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
rbentaarit
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
rbentaarit
Model Tree
Base
Qwen/Qwen3.5-2B
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
The kubelm-qwen3.5-2b-v1 LoRA adapter has been consolidated into the
single model repo alongside the Q4_K_M GGUF and model card:
rbentaarit/kubelm-qwen3.5-2b-v1The adapter now lives under adapter/ in that repo. This standalone
-lora repo is kept only so existing links keep resolving; it receives
no further updates. Pull the adapter from the consolidated repo:
python
from huggingface_hub import snapshot_downloadsnapshot_download("rbentaarit/kubelm-qwen3.5-2b-v1", allow_patterns="adapter/*")
For everything else (GGUF, serving instructions, eval numbers, provenance) see the consolidated repo's card.