Hugging Face's logo

mradermacher
/
Proctora-i1-GGUF

Transformers
GGUF
English
Mixture of Experts
Merge
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
0ccdd9d
·
verified ·
1 Parent(s): 6c2ed44

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -32,10 +32,30 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
36
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
 
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
 
 
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.4 | optimal size/speed/quality |
 
 
 
 
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
41
  types (lower is better):
 
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ1_S.gguf) | i1-IQ1_S | 2.8 | for the desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ1_M.gguf) | i1-IQ1_M | 3.1 | mostly desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.5 | very low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.7 | IQ3_XS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
47
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.3 | IQ3_S probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.8 | IQ3_M probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.0 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.4 | prefer IQ4_XS |
52
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q4_0.gguf) | i1-Q4_0 | 7.4 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.4 | optimal size/speed/quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.9 | fast, recommended |
55
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q4_1.gguf) | i1-Q4_1 | 8.2 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.0 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.2 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Proctora-i1-GGUF/resolve/main/Proctora.i1-Q6_K.gguf) | i1-Q6_K | 10.7 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
61
  types (lower is better):