Hugging Face's logo

mradermacher
/
Euclid-Project-Merged-FP16-i1-GGUF

Transformers
GGUF
English
imatrix
Model card Files
xet
Community
mradermacher commited on
Commit
7323ef1
·
verified ·
1 Parent(s): 49ee03a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -28,9 +28,30 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
31
  | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
 
 
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
 
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
 
 
 
 
 
34
 
35
  Here is a handy graph by ikawrakow comparing some lower-quality quant
36
  types (lower is better):
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
32
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
39
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
43
  | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.2 | prefer IQ4_XS |
49
  | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q4_1.gguf) | i1-Q4_1 | 4.7 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Euclid-Project-Merged-FP16-i1-GGUF/resolve/main/Euclid-Project-Merged-FP16.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):