You can deploy this model and start earning money today!

CelesteImperia/
Qwen2-VL-2B-Instruct-Platinum-GGUF

Name: Qwen2-VL-2B-Instruct-Platinum-GGUF
Availability: InStock

Qwen/Qwen2-VL-2B-Instruct

Views

No views yet

Qwen2-VL-2B-Instruct-GGUF (Platinum Series)

This repository contains the Platinum Series universal GGUF release of Qwen2-VL-2B-Instruct. This collection provides multiple quantization levels optimized for cross-platform vision tasks, including image understanding, document OCR, and visual reasoning.

📦 Available Files & Quantization Details

File Name	Quantization	Size	Accuracy	Recommended For
Qwen2-VL-2B-Instruct-Platinum-F16.gguf	FP16	~3.1 GB	100%	Master Reference / Benchmarking
Qwen2-VL-2B-Instruct-Platinum-Q8_0.gguf	Q8_0	~1.6 GB	99.9%	Platinum Reference / High-Fidelity
Qwen2-VL-2B-Instruct-Platinum-Q6_K.gguf	Q6_K	~1.3 GB	99.7%	High-Quality Vision Inference
Qwen2-VL-2B-Instruct-Platinum-Q5_K_M.gguf	Q5_K_M	~1.1 GB	99.2%	Balanced Desktop Performance
Qwen2-VL-2B-Instruct-Platinum-Q4_K_M.gguf	Q4_K_M	~1.0 GB	98.5%	Mobile / Edge Visual Reasoning

🐍 Python Inference (llama-cpp-python)

To run these engines using Python:

python

from llama_cpp import Llama

llm = Llama(
    model_path="Qwen2-VL-2B-Instruct-Platinum-Q8_0.gguf",
    n_gpu_layers=-1, # Target all layers to NVIDIA/Apple GPU
    n_ctx=4096,
    chat_format="qwen2_vl" # Specific handler for vision weights
)

# Note: Vision inference requires passing image data through the chat template

💻 For C# / .NET Users (LLamaSharp)

This collection is fully compatible with .NET applications via the LLamaSharp library.

csharp

using LLama.Common;
using LLama;

var parameters = new ModelParams("Qwen2-VL-2B-Instruct-Platinum-Q8_0.gguf") {
    ContextSize = 4096,
    GpuLayerCount = 35 
};

using var model = LLamaWeights.LoadFromFile(parameters);
using var context = model.CreateContext(parameters);
var executor = new InteractiveExecutor(context);

Console.WriteLine("Vision Engine Active.");

🏗️ Technical Details

Optimization Tool: llama.cpp (CUDA-accelerated)
Architecture: Qwen2-VL (2B)
Hardware Validation: Dual-GPU (RTX 3090 + RTX A4000)

☕ Support the Forge

Maintaining the production line for localized AI models requires significant hardware resources. If these tools power your research or industrial vision projects, please consider supporting the development:

Platform	Support Link
Global & India	Support via Razorpay

Scan to support via UPI (India Only):

Connect with the architect: Abhishek Jaiswal on LinkedIn

CelesteImperia/Qwen2-VL-2B-Instruct-Platinum-GGUF