by second-state
Open source · 9k downloads · 10 likes
Stable Diffusion 3.5 Medium GGUF is an AI model specialized in generating images from text descriptions, delivering advanced visual quality and creative flexibility. It enables the creation of illustrations, artwork, or realistic visuals by interpreting detailed prompts while optimizing performance through its quantized GGUF version. This model is particularly well-suited for artists, designers, and content creators looking to automate or accelerate their visual creation process. Its strength lies in balancing precision and speed while remaining accessible on a variety of hardware configurations.
stabilityai/stable-diffusion-3.5-medium
sd-api-server| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| clip_g-Q4_0.gguf | Q4_0 | 4 | 391 MB | |
| clip_g-Q4_1.gguf | Q4_1 | 4 | 435 MB | |
| clip_g-Q5_0.gguf | Q5_0 | 5 | 478 MB | |
| clip_g-Q5_1.gguf | Q5_1 | 5 | 522 MB | |
| clip_g-Q8_0.gguf | Q8_0 | 8 | 739 MB | |
| clip_g-f16.gguf | f16 | 16 | 1.39 GB | |
| clip_g.safetensors | f16 | 16 | 1.39 GB | |
| clip_l-Q4_0.gguf | Q4_0 | 4 | 69.4 MB | |
| clip_l-Q4_1.gguf | Q4_1 | 4 | 77.1 MB | |
| clip_l-Q5_0.gguf | Q5_0 | 5 | 84.8 MB | |
| clip_l-Q5_1.gguf | Q5_1 | 5 | 92.4 MB | |
| clip_l-Q8_0.gguf | Q8_0 | 8 | 131 MB | |
| clip_l-f16.gguf | f16 | 16 | 246 MB | |
| clip_l.safetensors | f16 | 16 | 246 MB | |
| sd3.5_medium-Q4_0.gguf | Q4_0 | 4 | 2.08 GB | |
| sd3.5_medium-Q4_1.gguf | Q4_1 | 4 | 2.22 GB | |
| sd3.5_medium-Q5_0.gguf | Q5_0 | 5 | 2.36 GB | |
| sd3.5_medium-Q5_1.gguf | Q5_1 | 5 | 2.50 GB | |
| sd3.5_medium-Q8_0.gguf | Q8_0 | 8 | 3.19 GB | |
| sd3.5_medium.safetensors | f16 | 16 | 5.11 GB | |
| t5xxl-Q4_0.gguf | Q4_0 | 4 | 2.75 GB | |
| t5xxl-Q4_1.gguf | Q4_1 | 4 | 3.06 GB | |
| t5xxl-Q5_0.gguf | Q5_0 | 5 | 3.36 GB | |
| t5xxl-Q5_1.gguf | Q5_1 | 5 | 3.67 GB | |
| t5xxl-Q8_0.gguf | Q8_0 | 8 | 5.20 GB | |
| t5xxl_fp16.safetensors | f16 | 16 | 9.79 GB |
Quantized with stable-diffusion.cpp master-c3eeb669.