mradermacher
commited on
Commit
•
d656394
1
Parent(s):
d769b8f
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -20,6 +20,8 @@ more details, including on how to concatenate multi-part files.
|
|
20 |
|
21 |
## Provided Quants
|
22 |
|
|
|
|
|
23 |
| Link | Type | Size/GB | Notes |
|
24 |
|:-----|:-----|--------:|:------|
|
25 |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.7 | |
|
@@ -38,4 +40,8 @@ more details, including on how to concatenate multi-part files.
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.4 | best weighted quant |
|
39 |
|
40 |
|
|
|
|
|
|
|
|
|
41 |
<!-- end -->
|
|
|
20 |
|
21 |
## Provided Quants
|
22 |
|
23 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
24 |
+
|
25 |
| Link | Type | Size/GB | Notes |
|
26 |
|:-----|:-----|--------:|:------|
|
27 |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.7 | |
|
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.4 | best weighted quant |
|
41 |
|
42 |
|
43 |
+
Here is a handy table comparing some lower-quality quant types:
|
44 |
+
|
45 |
+
![image.png](https://cdn-uploads.huggingface.co/production/uploads/645ce413a19f3e64bbeece31/dEiT6xDvxyANdetzVG1tX.png)
|
46 |
+
|
47 |
<!-- end -->
|