Update README.md
Browse files
README.md
CHANGED
|
@@ -9,8 +9,19 @@ tags:
|
|
| 9 |
- imatrix
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## Experimental from q8
|
| 13 |
|
| 14 |
| Filename | Quant type | File Size | Description |
|
| 15 |
| -------- | ---------- | --------- | ----------- |
|
| 16 |
-
| [flux1-dev-IQ1_S.gguf](https://huggingface.co/Eviation/flux-imatrix/blob/main/experimental-from-q8/flux1-dev-IQ1_S.gguf) | IQ1_S | 2.45GB | TBC |
|
|
|
|
|
|
|
|
|
| 9 |
- imatrix
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Support
|
| 13 |
+
|
| 14 |
+
- ComfyUI-GGUF: TBC
|
| 15 |
+
- Forge: TBC
|
| 16 |
+
- stable-diffusion.cpp: [llama.cpp Feature-matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
|
| 17 |
+
|
| 18 |
+
# Alpha
|
| 19 |
+
simple imatrix: 512x512 single image 8/20 steps q3_K_S euler data: `load_imatrix: loaded 314 importance matrix entries from imatrix.dat computed on 7 chunks`
|
| 20 |
+
|
| 21 |
## Experimental from q8
|
| 22 |
|
| 23 |
| Filename | Quant type | File Size | Description |
|
| 24 |
| -------- | ---------- | --------- | ----------- |
|
| 25 |
+
| [flux1-dev-IQ1_S.gguf](https://huggingface.co/Eviation/flux-imatrix/blob/main/experimental-from-q8/flux1-dev-IQ1_S.gguf) | IQ1_S | 2.45GB | TBC |
|
| 26 |
+
| [flux1-dev-IQ2_XXS.gguf](https://huggingface.co/Eviation/flux-imatrix/blob/main/experimental-from-q8/flux1-dev-IQ2_XXS.gguf) | IQ1_S | 2.96GB | TBC |
|
| 27 |
+
|