mradermacher
commited on
Commit
•
73d4c79
1
Parent(s):
ace1ad7
auto-patch README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ more details, including on how to concatenate multi-part files.
|
|
27 |
| Link | Type | Size/GB | Notes |
|
28 |
|:-----|:-----|--------:|:------|
|
29 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 9.8 | for the desperate |
|
30 |
-
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 10.1 |
|
31 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.0 | |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 13.2 | |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 14.0 | |
|
@@ -48,7 +48,6 @@ more details, including on how to concatenate multi-part files.
|
|
48 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.2 | |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 35.1 | practically like static Q6_K |
|
50 |
|
51 |
-
|
52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
53 |
types (lower is better):
|
54 |
|
|
|
27 |
| Link | Type | Size/GB | Notes |
|
28 |
|:-----|:-----|--------:|:------|
|
29 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 9.8 | for the desperate |
|
30 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 10.1 | mostly desperate |
|
31 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.0 | |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 13.2 | |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 14.0 | |
|
|
|
48 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.2 | |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 35.1 | practically like static Q6_K |
|
50 |
|
|
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
52 |
types (lower is better):
|
53 |
|