gpustack commited on
Commit
5cd3726
·
verified ·
1 Parent(s): 8e4ef87

docs: readme

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -16,6 +16,15 @@ tags:
16
  **Original model**: [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell)<br/>
17
  **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
18
 
 
 
 
 
 
 
 
 
 
19
  ---
20
 
21
  ![FLUX.1 [schnell] Grid](./schnell_grid.jpeg)
 
16
  **Original model**: [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell)<br/>
17
  **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
18
 
19
+ | Quantization | OpenAI CLIP ViT-L/14 Quantization | Google T5-xxl Quantization | VAE Quantization |
20
+ | --- | --- | --- | --- |
21
+ | FP16 | FP16 | FP16 | FP16 |
22
+ | Q8_0 | FP16 | Q8_0 | FP16 |
23
+ | (pure) Q8_0 | Q8_0 | Q8_0 | FP16 |
24
+ | Q4_1 | FP16 | Q8_0 | FP16 |
25
+ | Q4_0 | FP16 | Q8_0 | FP16 |
26
+ | (pure) Q4_0 | Q4_0 | Q4_0 | FP16 |
27
+
28
  ---
29
 
30
  ![FLUX.1 [schnell] Grid](./schnell_grid.jpeg)