qwen3-vl-2b-dynamic-ptq

This repository contains a quantized model artifact produced in the graduation project.

Model Details

• Technique: PTQ
• Quantization: Dynamic PTQ
• Base model: Qwen/Qwen3-VL-2B-Instruct
• Export date: 2026-03-24

Benchmark Summary

Metric	Original	Quantized
Disk size (GB)	N/A	N/A
Avg inference time	N/A	N/A
Tokens/sec	N/A	N/A
GPU memory	N/A	N/A

Comparison Highlights

• Speedup: N/Ax
• Memory reduction: N/A%
• Disk/model size reduction: N/A%

Benchmark Notes

• Local benchmark file contains an error for original model load.
• Local benchmark file contains an error for quantized model load.

Local Source

• Quantized folder: Basic-Techniques/PTQ-Post-Training-Quantization/quantized/qwen3vl_dynamic_ptq
• Benchmark JSON: Basic-Techniques/PTQ-Post-Training-Quantization/benchmark_results/ptq_benchmark_results.json

Usage

Use the model with the library and runtime that match the quantization technique in this repo.

Limitations

• This model card is auto-generated from project files.
• You should validate quality, safety, and license compatibility before public release.