mradermacher
commited on
Commit
•
d0a16f8
1
Parent(s):
5682bc3
auto-patch README.md
Browse files
README.md
CHANGED
@@ -45,10 +45,15 @@ more details, including on how to concatenate multi-part files.
|
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q2_K.gguf) | i1-Q2_K | 13.4 | IQ3_XXS probably better |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 14.2 | fast, lower quality |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.9 | |
|
|
|
48 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_S.gguf) | i1-IQ3_S | 15.8 | fast, beats Q3_K* |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_M.gguf) | i1-IQ3_M | 16.1 | |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.5 | IQ3_S probably better |
|
|
|
|
|
51 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 22.1 | fast, medium quality |
|
|
|
|
|
52 |
|
53 |
|
54 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q2_K.gguf) | i1-Q2_K | 13.4 | IQ3_XXS probably better |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 14.2 | fast, lower quality |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.9 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.8 | IQ3_XS probably better |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_S.gguf) | i1-IQ3_S | 15.8 | fast, beats Q3_K* |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-IQ3_M.gguf) | i1-IQ3_M | 16.1 | |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.5 | IQ3_S probably better |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 19.0 | IQ3_M probably better |
|
53 |
+
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.8 | almost as good as Q4_K_M |
|
54 |
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 22.1 | fast, medium quality |
|
55 |
+
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 25.1 | |
|
56 |
+
| [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-i1-GGUF/resolve/main/Umbra-v3-MoE-4x11b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.9 | best weighted quant |
|
57 |
|
58 |
|
59 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|