Update README.md
Browse files
README.md
CHANGED
|
@@ -9,5 +9,7 @@ Based on `FLUX.1 [schnell]` with heavy architectural modifications.
|
|
| 9 |
|
| 10 |
Quantized into GGUF format using a modified llama.cpp & city96's ComfyUI-GGUF/tools. Distillation layers are not quantized.
|
| 11 |
|
|
|
|
|
|
|
| 12 |
Q*_M GGUFs are mixed quantizations with an aim at maximizing speed by selectively choosing the quantization of certain layers.
|
| 13 |
- Q8_M focuses on Q8_0 quantization of weights for performance, mixed with Q6_K on less heavy layers.
|
|
|
|
| 9 |
|
| 10 |
Quantized into GGUF format using a modified llama.cpp & city96's ComfyUI-GGUF/tools. Distillation layers are not quantized.
|
| 11 |
|
| 12 |
+
Also see [silveroxides'](https://huggingface.co/Clybius/Chroma-GGUF/edit/main/README.md) Chroma GGUFs! (BF16, Q8_0, Q6_K, Q5_K_S, Q5_1, Q5_0, Q4_K_M, Q4_1, Q4_0, Q3_K_L)
|
| 13 |
+
|
| 14 |
Q*_M GGUFs are mixed quantizations with an aim at maximizing speed by selectively choosing the quantization of certain layers.
|
| 15 |
- Q8_M focuses on Q8_0 quantization of weights for performance, mixed with Q6_K on less heavy layers.
|