Commit
•
08a218b
1
Parent(s):
1350f85
auto-patch README.md
Browse files
README.md
CHANGED
@@ -76,7 +76,7 @@ more details, including on how to concatenate multi-part files.
|
|
76 |
| Link | Type | Size/GB | Notes |
|
77 |
|:-----|:-----|--------:|:------|
|
78 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
|
79 |
-
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 |
|
80 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
|
81 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
|
82 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
|
@@ -97,7 +97,6 @@ more details, including on how to concatenate multi-part files.
|
|
97 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
|
98 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
99 |
|
100 |
-
|
101 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
102 |
types (lower is better):
|
103 |
|
|
|
76 |
| Link | Type | Size/GB | Notes |
|
77 |
|:-----|:-----|--------:|:------|
|
78 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
|
79 |
+
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
|
80 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
|
81 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
|
82 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
|
|
|
97 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
|
98 |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
99 |
|
|
|
100 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
101 |
types (lower is better):
|
102 |
|