Update README.md
Browse files
README.md
CHANGED
@@ -22,13 +22,15 @@ Only the second layers of both MLPs in each MMDiT block of SD3.5 Large models ha
|
|
22 |
|
23 |
- [sd3.5_large_turbo-q2_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q2_k_4_0.gguf): Smallest quantization yet. Use this if you can't afford anything bigger
|
24 |
- [sd3.5_large_turbo-q3_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q3_k_4_0.gguf): Smaller than q4_0, acceptable degradation.
|
25 |
-
- [sd3.5_large_turbo-q4_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_4_0.gguf): Exacty same size as q4_0,
|
26 |
- [sd3.5_large_turbo-q4_k_4_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_4_1.gguf): Smaller than q4_1, and with comparable degradation. Recommended
|
27 |
- [sd3.5_large_turbo-q4_k_5_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_5_0.gguf): Smaller than q5_0, and with comparable degradation. Very close to the original f16 already. Recommended
|
28 |
|
29 |
### Legacy types:
|
30 |
|
31 |
-
- [sd3.5_large_turbo-
|
|
|
|
|
32 |
- [sd3.5_large_turbo-q4_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q4_1.gguf): Not recommended (q4_k_4_1 is better and smaller)
|
33 |
- [sd3.5_large_turbo-q5_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q5_0.gguf): Barely better and bigger than q4_k_5_0
|
34 |
- [sd3.5_large_turbo-q5_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q5_1.gguf): Better and bigger than q5_0
|
@@ -36,7 +38,7 @@ Only the second layers of both MLPs in each MMDiT block of SD3.5 Large models ha
|
|
36 |
|
37 |
## Outputs:
|
38 |
|
39 |
-
Sorted by model size (Note that q4_0 and
|
40 |
|
41 |
| Quantization | Robot girl | Text | Cute kitten |
|
42 |
| ------------------ | -------------------------------- | ---------------------------------- | ---------------------------------- |
|
@@ -44,6 +46,7 @@ Sorted by model size (Note that q4_0 and q4_k_4_0 are the exact same size)
|
|
44 |
| q3_k_4_0 |  |  |  |
|
45 |
| q4_0 |  |  |  |
|
46 |
| q4_k_4_0 |  |  |  |
|
|
|
47 |
| q4_k_4_1 |  |  |  |
|
48 |
| q4_1 |  |  |  |
|
49 |
| q4_k_5_0 |  |  |  |
|
|
|
22 |
|
23 |
- [sd3.5_large_turbo-q2_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q2_k_4_0.gguf): Smallest quantization yet. Use this if you can't afford anything bigger
|
24 |
- [sd3.5_large_turbo-q3_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q3_k_4_0.gguf): Smaller than q4_0, acceptable degradation.
|
25 |
+
- [sd3.5_large_turbo-q4_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_4_0.gguf): Exacty same size as q4_0 and iq4_nl, I recommend using iq4_nl instead.
|
26 |
- [sd3.5_large_turbo-q4_k_4_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_4_1.gguf): Smaller than q4_1, and with comparable degradation. Recommended
|
27 |
- [sd3.5_large_turbo-q4_k_5_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_5_0.gguf): Smaller than q5_0, and with comparable degradation. Very close to the original f16 already. Recommended
|
28 |
|
29 |
### Legacy types:
|
30 |
|
31 |
+
- [sd3.5_large_turbo-iq4_nl.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-iq4_nl.gguf): Same size as q4_k_4_0 and q4_0, runs faster than q4_k_4_0 (on Vulkan at least), and provides better image quality. Recommended
|
32 |
+
|
33 |
+
- [sd3.5_large_turbo-q4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q4_0.gguf): Same size as q4_k_4_0, Not recommended (use iqk_nl q4_k_4_0 instead)
|
34 |
- [sd3.5_large_turbo-q4_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q4_1.gguf): Not recommended (q4_k_4_1 is better and smaller)
|
35 |
- [sd3.5_large_turbo-q5_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q5_0.gguf): Barely better and bigger than q4_k_5_0
|
36 |
- [sd3.5_large_turbo-q5_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q5_1.gguf): Better and bigger than q5_0
|
|
|
38 |
|
39 |
## Outputs:
|
40 |
|
41 |
+
Sorted by model size (Note that q4_0, q4_k_4_0, and iq4_nl are the exact same size)
|
42 |
|
43 |
| Quantization | Robot girl | Text | Cute kitten |
|
44 |
| ------------------ | -------------------------------- | ---------------------------------- | ---------------------------------- |
|
|
|
46 |
| q3_k_4_0 |  |  |  |
|
47 |
| q4_0 |  |  |  |
|
48 |
| q4_k_4_0 |  |  |  |
|
49 |
+
| iq4_nl |  |  |  |
|
50 |
| q4_k_4_1 |  |  |  |
|
51 |
| q4_1 |  |  |  |
|
52 |
| q4_k_5_0 |  |  |  |
|