Hugging Face's logo

mradermacher
/
MixtralOrochi8x7B-i1-GGUF

Transformers
GGUF
English
mixtral
uncensored
high-intelligence
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
4c5dc1a
•
1 Parent(s): 847feee

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  language:
3
  - en
4
  library_name: transformers
@@ -13,7 +14,6 @@ tags:
13
 
14
  weighted/imatrix quants of https://huggingface.co/smelborp/MixtralOrochi8x7B
15
 
16
-
17
  <!-- provided-files -->
18
  static quants are available at https://huggingface.co/mradermacher/MixtralOrochi8x7B-GGUF
19
  ## Usage
@@ -28,12 +28,16 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
31
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q2_K.gguf) | i1-Q2_K | 17.6 | IQ3_XXS probably better |
32
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.7 | IQ3_XS probably better |
33
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
34
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
 
35
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
36
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
38
 
39
 
 
1
  ---
2
+ exported_from: smelborp/MixtralOrochi8x7B
3
  language:
4
  - en
5
  library_name: transformers
 
14
 
15
  weighted/imatrix quants of https://huggingface.co/smelborp/MixtralOrochi8x7B
16
 
 
17
  <!-- provided-files -->
18
  static quants are available at https://huggingface.co/mradermacher/MixtralOrochi8x7B-GGUF
19
  ## Usage
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-IQ2_M.gguf) | i1-IQ2_M | 15.8 | |
32
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q2_K.gguf) | i1-Q2_K | 17.6 | IQ3_XXS probably better |
33
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.7 | IQ3_XS probably better |
34
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
35
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
36
+ | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
37
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
38
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.5 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
41
  | [GGUF](https://huggingface.co/mradermacher/MixtralOrochi8x7B-i1-GGUF/resolve/main/MixtralOrochi8x7B.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
42
 
43