Hugging Face's logo

mradermacher
/
YugoGPT-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
9364a06
•
1 Parent(s): b07f045

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -29,19 +29,29 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
32
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
33
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
34
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
 
35
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
36
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
37
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
 
38
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
 
39
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
40
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
 
 
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
44
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
33
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
34
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
35
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
41
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
43
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
44
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
55
  | [GGUF](https://huggingface.co/mradermacher/YugoGPT-i1-GGUF/resolve/main/YugoGPT.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant