README.md
1.8 KB · 35 lines · markdown Raw
1 ---
2 base_model: SulphurAI/Sulphur-2-base
3 library_name: gguf
4 pipeline_tag: text-to-video
5 tags:
6 - gguf
7 - quantized
8 ---
9
10 # Sulphur-2-Base (Dev) - GGUF
11
12 This repository contains GGUF format model files for [SulphurAI's Sulphur-2-base](https://huggingface.co/SulphurAI/Sulphur-2-base).
13
14 ## Model Details
15 * **Original Model:** [SulphurAI/Sulphur-2-base](https://huggingface.co/SulphurAI/Sulphur-2-base)
16 * **Format:** GGUF
17 * **Architecture:** ltxv
18 * **Model Size:** 21B parameters
19
20 ## Available Quantizations
21
22 The following quantization tiers are provided to accommodate different hardware capabilities and VRAM constraints.
23
24 | Filename | Quantization Type | Size | Recommended Use |
25 |:---|:---|:---|:---|
26 | `sulphur_dev_bf16.gguf` | BF16 (16-bit) | 42.0 GB | Unquantized baseline. Maximum quality and accuracy. Requires massive VRAM. |
27 | `sulphur_dev-Q8_0.gguf` | Q8_0 (8-bit) | 22.8 GB | Extremely high quality, near unquantized performance. |
28 | `sulphur_dev-Q6_K.gguf` | Q6_K (6-bit) | 17.8 GB | Very high quality, minimal precision loss. |
29 | `sulphur_dev-Q5_K_M.gguf` | Q5_K_M (5-bit) | 16.1 GB | Excellent balance of quality and performance. |
30 | `sulphur_dev-Q5_K_S.gguf` | Q5_K_S (5-bit) | 15.0 GB | Slightly smaller 5-bit variant for strict memory limits. |
31 | `sulphur_dev-Q4_K_M.gguf` | Q4_K_M (4-bit) | 14.3 GB | Recommended standard. Fast inference with very low quality degradation. |
32 | `sulphur_dev-Q4_K_S.gguf` | Q4_K_S (4-bit) | 13.2 GB | Smaller 4-bit variant, slightly lower quality than K_M. |
33 | `sulphur_dev-Q4_0.gguf` | Q4_0 (4-bit) | 13.0 GB | Legacy 4-bit quant. Very fast inference but higher perplexity than K-quants. |
34 | `sulphur_dev-Q3_K_M.gguf` | Q3_K_M (3-bit) | 11.1 GB | High compression. Best for constrained environments with limited RAM/VRAM. |
35 | `sulphur_dev-Q3_K_S.gguf` | Q3_K_S (3-bit) | 10.3 GB | Maximum compression. Lowest footprint but highest quality loss. |