GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
DatasetMan
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
DatasetMan
Model Tree
Qwen/Qwen3-VL-8B-Thinking
Input Modalities
Output Modalities
Supported Functionality
Qwen3VLForConditionalGenerationQwen/Qwen3-VL-8B-Thinkingpython
from transformers import AutoProcessor, Qwen3VLForConditionalGenerationmodel_id = "DatasetMan/QGO-8B"model = Qwen3VLForConditionalGeneration.from_pretrained(model_id,dtype="auto",device_map="auto",)processor = AutoProcessor.from_pretrained(model_id)
The full BF16 weights are approximately 17.5 GB before runtime allocations. Plan GPU/CPU memory for weights, vision inputs, KV cache, and generation in addition to the checkpoint size.
Use the base model's official chat template and greedy decoding for PM4Bench evaluation. Task prompts and evaluation code are provided in https://github.com/opendatalab/PM4Bench.
The released data is available at
https://huggingface.co/datasets/DatasetMan/PM4Bench-QGO-Train. The recipe
uses 32 prompts and 8 rollouts per prompt (256 trajectories per step), AdamW
with learning rate 1e-6, BF16, and eight GPUs.
| Model | MDUR trad. | MDUR vision | MIQA trad. | MIQA vision | MSOCR | MGUI |
|---|---|---|---|---|---|---|
| Qwen3-VL-8B-Thinking | 38.55 | 34.88 | 53.63 | 47.69 | 1.53 | 78.30 |
| QGO-8B | 46.82 | 40.84 | 55.24 | 51.06 | 8.17 | 80.00 |
These are the audited paper results. MDUR and MGUI are percentages, MIQA is the six-dimension judge score on a 10-100 scale, and MSOCR is on a 0-40 scale.
QGO-8B targets multilingual OCR robustness. It inherits limitations and risks from the Qwen base model and is not guaranteed to improve every downstream task or language. Coordinate outputs, OCR transcriptions, and long-form reasoning should be validated before use in consequential applications.