ViCoder Preview
Collection
Preview release of the ViCoder model series by VicharAI
β’
2 items
β’
Updated
β’
3
ViCoder-HTML-32B-preview
is a powerful AI model designed to generate full websites, including HTML, Tailwind CSS, and JavaScript.
This model comes in several quantizations, each offering a balance of file size and performance. Choose the one that best suits your memory and quality requirements.
Quantization | Size (GB) | Expected Quality | Notes |
---|---|---|---|
Q8_0 | 34.8 | π’ Very good β nearly full precision | 8-bit quantization, very close to full precision for most tasks. |
Q6_K | 26.9 | π’ Good β retains most performance | 6-bit quantization, high quality, efficient for most applications. |
Q4_K_M | 19.9 | π‘ Moderate β usable with minor degradation | 4-bit quantization, good tradeoff between quality and size. |
Q3_K_M | 15.9 | π Lower β may lose accuracy, better for small RAM | 3-bit quantization, lower quality, best for minimal memory use. |
3-bit
4-bit
6-bit
8-bit
Base model
Qwen/Qwen2.5-32B