Transformers
GGUF
English
Inference Endpoints
conversational
mradermacher commited on
Commit
8fa1f32
·
verified ·
1 Parent(s): 16232ec

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -32,7 +32,27 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | for the desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
45
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Crunchy-onion-i1-GGUF/resolve/main/Crunchy-onion.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
56
 
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant