GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
JasperHaozhe
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
JasperHaozhe
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
Install a recent vLLM release, download
serve_evaluator.sh,
and run:
bash
pip install vllmbash serve_evaluator.sh
The endpoint is OpenAI-compatible and serves the model as
AgentGen-Bench-Evaluator on port 7070.
Two serving details are required:
--chat-template-content-format openai. The evaluator consumes
multimodal OpenAI-style message content; relying on automatic format
detection can produce incompatible requests.bash serve_evaluator.sh --gpus 0,1,2,3 starts four data-parallel replicas
with tensor parallel size one. The script derives the data-parallel size
from the GPU list; --dp and --tp remain available for custom layouts.An equivalent direct command is:
bash
CUDA_VISIBLE_DEVICES=0,1,2,3 vllm serve JasperHaozhe/AgentGen-Bench-Evaluator \--served-model-name AgentGen-Bench-Evaluator \--chat-template-content-format openai \--max-model-len 20480 \--limit-mm-per-prompt '{"image": 8, "video": 0}' \--tensor-parallel-size 1 \--data-parallel-size 4 \--gpu-memory-utilization 0.75 \--port 7070
Use the endpoint with the released evaluation code and setup.
This checkpoint is intended to reproduce AgentGen-Bench evaluation of generated images across knowledge and rendering dimensions. Like any learned judge, it may inherit biases from its training data and base model. Scores should be interpreted using the released protocol and aggregated across the benchmark, not as definitive judgments of individual images.
Apache-2.0. Users must also comply with the terms of the Qwen3.5-9B base model.