mradermacher
commited on
Commit
•
43611fe
1
Parent(s):
6b6a2fd
auto-patch README.md
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ more details, including on how to concatenate multi-part files.
|
|
24 |
| Link | Type | Size/GB | Notes |
|
25 |
|:-----|:-----|--------:|:------|
|
26 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate |
|
27 |
-
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ1_M.gguf) | i1-IQ1_M | 3.5 |
|
28 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.9 | |
|
29 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.2 | |
|
30 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | |
|
@@ -38,7 +38,7 @@ more details, including on how to concatenate multi-part files.
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.6 | IQ3_S probably better |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.2 | IQ3_M probably better |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.3 | |
|
41 |
-
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.7 |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q4_0.gguf) | i1-Q4_0 | 7.7 | fast, low quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.7 | optimal size/speed/quality |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.2 | fast, recommended |
|
@@ -46,7 +46,6 @@ more details, including on how to concatenate multi-part files.
|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.5 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q6_K.gguf) | i1-Q6_K | 11.0 | practically like static Q6_K |
|
48 |
|
49 |
-
|
50 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
51 |
types (lower is better):
|
52 |
|
|
|
24 |
| Link | Type | Size/GB | Notes |
|
25 |
|:-----|:-----|--------:|:------|
|
26 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate |
|
27 |
+
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ1_M.gguf) | i1-IQ1_M | 3.5 | mostly desperate |
|
28 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.9 | |
|
29 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.2 | |
|
30 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | |
|
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.6 | IQ3_S probably better |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.2 | IQ3_M probably better |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.3 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.7 | prefer IQ4_XS |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q4_0.gguf) | i1-Q4_0 | 7.7 | fast, low quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.7 | optimal size/speed/quality |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.2 | fast, recommended |
|
|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.5 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/MythoLogic-L2-13b-i1-GGUF/resolve/main/MythoLogic-L2-13b.i1-Q6_K.gguf) | i1-Q6_K | 11.0 | practically like static Q6_K |
|
48 |
|
|
|
49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
50 |
types (lower is better):
|
51 |
|