mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -28,7 +28,24 @@ more details, including on how to concatenate multi-part files.
|
|
28 |
|
29 |
| Link | Type | Size/GB | Notes |
|
30 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
31 |
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
|
34 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
28 |
|
29 |
| Link | Type | Size/GB | Notes |
|
30 |
|:-----|:-----|--------:|:------|
|
31 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
|
32 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | |
|
33 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.6 | |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.7 | lower quality |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.7 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.4 | beats Q3_K* |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.4 | IQ3_XS probably better |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.2 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.1 | IQ3_S probably better |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.6 | IQ3_M probably better |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.8 | optimal size/speed/quality |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
|
49 |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|