Modelpublic

aman5g/Sulphur-2-base-GGUF

sourceHugging Faceupdated 4mo agoView on Hugging Face

3likes613downloads

Model Card

Sulphur-2-Base (Dev) - GGUF

This repository contains GGUF format model files for SulphurAI's Sulphur-2-base.

The following quantization tiers are provided to accommodate different hardware capabilities and VRAM constraints.

Filename	Quantization Type	Recommended Use
`sulphur_dev_bf16.gguf`	BF16	Unquantized baseline (16-bit). Maximum quality and accuracy. Requires massive VRAM (42GB+).
`sulphur_dev-Q8_0.gguf`	Q8_0	Extremely high quality, near unquantized performance. Requires high VRAM.
`sulphur_dev-Q6_K.gguf`	Q6_K	Very high quality, minimal precision loss.
`sulphur_dev-Q5_K_M.gguf`	Q5KM	Excellent balance of quality and performance.
`sulphur_dev-Q4_K_M.gguf`	Q4KM	Recommended standard. Fast inference with very low quality degradation.
`sulphur_dev-Q3_K_M.gguf`	Q3KM	High compression. Best for constrained environments with limited RAM/VRAM.