GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
objectai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
objectai
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
bash
vllm serve objectai/obj_v1 \ --served-model-name obj_v1 \ --max-model-len 16384 \ --limit-mm-per-prompt '{"image":1}' \ --mm-processor-kwargs '{"max_pixels":1003520}' \ --trust-remote-codemax_pixels is 1280x28x28, the resolution the model was trained at. Raising it
wastes KV cache; lowering it makes small print unreadable.
The server is OpenAI-compatible, so an ordinary chat completion works:
python
import base64, json, openaiclient = openai.OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")image = base64.b64encode(open("cheque.jpg", "rb").read()).decode()schema = {"cheque_details": {"amount": "number", "payee": "string", "date": "string", "cheque_number": "string"}}response = client.chat.completions.create( model="obj_v1", temperature=0.0, max_tokens=8192, messages=[ {"role": "system", "content": "You are a document data extraction model. " "Extract only values present in the document. " "Use null for fields that are absent or illegible. " "Output a single compact JSON object matching the requested schema. " "No prose, no markdown, no explanation."}, {"role": "user", "content": [ {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image}"}}, {"type": "text", "text": f"document_type: cheque\nschema: {json.dumps(schema)}"}, ]}, ],)print(response.choices[0].message.content)Match training or accuracy drops. The system prompt above is verbatim, and the user turn is the image followed by exactly two lines:
text
document_type: <type>schema: <compact json>Set temperature=0.0 so the same page yields the same answer.
| Weights | 8.9 GB (bf16) |
| VRAM | 16 GB minimum, 24 GB comfortable |
| Precision | bf16 (Ampere or newer; use fp16 below that) |
| Context | 16384 covers the longest documents |
Runs on an L4, A10G, L40S, A100 or RTX 4090. On a T4 add --dtype float16. |
Compact JSON matching the requested schema. Fields absent from the page come
back null rather than guessed. Values found on the page that the schema did
not ask for are placed under extras when that key is included in the schema.
Apache 2.0. Fine-tuned from Qwen3-VL-4B-Instruct, which is Apache 2.0.
vllm serve objectai/obj_v1 \ --served-model-name obj_v1 \ --max-model-len 16384 \ --limit-mm-per-prompt '{"image":1}' \ --mm-processor-kwargs '{"max_pixels":1003520}' \ --trust-remote-codeimport base64, json, openaiclient = openai.OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")image = base64.b64encode(open("cheque.jpg", "rb").read()).decode()schema = {"cheque_details": {"amount": "number", "payee": "string", "date": "string", "cheque_number": "string"}}response = client.chat.completions.create( model="obj_v1", temperature=0.0, max_tokens=8192, messages=[ {"role": "system", "content": "You are a document data extraction model. " "Extract only values present in the document. " "Use null for fields that are absent or illegible. " "Output a single compact JSON object matching the requested schema. " "No prose, no markdown, no explanation."}, {"role": "user", "content": [ {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image}"}}, {"type": "text", "text": f"document_type: cheque\nschema: {json.dumps(schema)}"}, ]}, ],)print(response.choices[0].message.content)