GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CYX1998
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CYX1998
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
<tool_call> support via Hermes format, compatible with vLLM's tool-call parser<think> chain-of-thought reasoning before actions| Base model | Qwen3-VL-4B-Instruct |
| Architecture | Qwen3VLForConditionalGeneration |
| Parameters | 4B |
| Precision | bfloat16 |
| Training method | LoRA SFT (rank=32, alpha=64), merged |
| Training data | 43,210 medical agentic trajectories (open subset) |
| Training framework | LLaMA-Factory |
| Context length | 8,192 tokens (training) |
| Tested environment | transformers 4.57.0, vLLM 0.11.0 |
python
from transformers import AutoModelForImageTextToText, AutoProcessorimport torch model = AutoModelForImageTextToText.from_pretrained( "CYX1998/Meissa-4B", torch_dtype=torch.bfloat16, device_map="auto",)processor = AutoProcessor.from_pretrained("CYX1998/Meissa-4B")For agentic use cases, serve Meissa with vLLM to enable tool calling:
bash
python -m vllm.entrypoints.openai.api_server \ --model CYX1998/Meissa-4B \ --port 8877 \ --max-model-len 8192 \ --gpu-memory-utilization 0.85 \ --dtype bfloat16 \ --enable-auto-tool-choice \ --tool-call-parser hermes # Set the endpointexport OPENAI_BASE_URL="http://127.0.0.1:8877/v1"export OPENAI_API_KEY="dummy"The --enable-auto-tool-choice --tool-call-parser hermes flags are required for tool calling.
python
from openai import OpenAI client = OpenAI(base_url="http://127.0.0.1:8877/v1", api_key="dummy") tools = [{ "type": "function", "function": { "name": "ChestXRayClassifier", "description": "Classify pathologies in a chest X-ray image.", "parameters": { "type": "object", "properties": { "image_path": {"type": "string", "description": "Path to the chest X-ray image"} }, "required": ["image_path"] } }}] response = client.chat.completions.create( model="CYX1998/Meissa-4B", messages=[{"role": "user", "content": "Analyze this chest X-ray: /path/to/cxr.jpg"}], tools=tools,)print(response.choices[0].message)| Framework | Description | Tools |
|---|---|---|
| I: Continuous Tool Calling | Sequential tool use for radiology analysis | 8 chest X-ray tools (classifier, report generator, VQA, segmentation, etc.) |
| II: Interleaved Thinking with Images | Iterative visual reasoning with zoom | ZoomInSubfigure, SegmentRegion, Terminate |
| III: Multi-Agent Collaboration | Multi-agent medical consultation | AssessDifficulty, RecruitExperts, ConsultExperts, FacilitateDebate |
| IV: Clinical Simulation | Multi-turn doctor-patient interaction | RequestPhysicalExam, RequestTest, Terminate |
Trained on 43,210 medical agentic SFT trajectories distilled from Gemini:
| Framework | Samples | Source Datasets |
|---|---|---|
| I: Continuous Tool Calling | 4,898 | MIMIC-CXR-VQA |
| II: Interleaved Thinking | 15,211 | PathVQA, MIMIC-CXR-VQA, SLAKE, VQA-RAD |
| III: Multi-Agent Collaboration | 15,427 | MIMIC-CXR-VQA, PathVQA, MedQA, PubMedQA |
| IV: Clinical Simulation | 7,674 | MedQA, MIMIC-CXR |
The open-source subset (25,018 samples) is available at CYX1998/Meissa-SFT.
Meissa-4B matches or exceeds GPT-4o and Gemini-3-flash on multiple medical agentic benchmarks while being deployable offline on a single GPU. See our paper for full results.
bibtex
@inproceedings{chen2026meissa, title={Meissa: Multi-modal Medical Agentic Intelligence}, author={Chen, Yixiong and Bai, Xinyi and Pan, Yue and Zhou, Zongwei and Yuille, Alan}, journal={arXiv preprint arXiv:2603.09018}, year={2026}}This model is released under Apache 2.0. The base model Qwen3-VL-4B-Instruct is subject to the Qwen License.
from transformers import AutoModelForImageTextToText, AutoProcessorimport torch model = AutoModelForImageTextToText.from_pretrained( "CYX1998/Meissa-4B", torch_dtype=torch.bfloat16, device_map="auto",)processor = AutoProcessor.from_pretrained("CYX1998/Meissa-4B")python -m vllm.entrypoints.openai.api_server \ --model CYX1998/Meissa-4B \ --port 8877 \ --max-model-len 8192 \ --gpu-memory-utilization 0.85 \ --dtype bfloat16 \ --enable-auto-tool-choice \ --tool-call-parser hermes # Set the endpointexport OPENAI_BASE_URL="http://127.0.0.1:8877/v1"export OPENAI_API_KEY="dummy"from openai import OpenAI client = OpenAI(base_url="http://127.0.0.1:8877/v1", api_key="dummy") tools = [{ "type": "function", "function": { "name": "ChestXRayClassifier", "description": "Classify pathologies in a chest X-ray image.", "parameters": { "type": "object", "properties": { "image_path": {"type": "string", "description": "Path to the chest X-ray image"} }, "required": ["image_path"] } }}] response = client.chat.completions.create( model="CYX1998/Meissa-4B", messages=[{"role": "user", "content": "Analyze this chest X-ray: /path/to/cxr.jpg"}], tools=tools,)print(response.choices[0].message)@inproceedings{chen2026meissa, title={Meissa: Multi-modal Medical Agentic Intelligence}, author={Chen, Yixiong and Bai, Xinyi and Pan, Yue and Zhou, Zongwei and Yuille, Alan}, journal={arXiv preprint arXiv:2603.09018}, year={2026}}