Hugging Face's logo

mradermacher
/
Yislerp6-34B-i1-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
209d159
•
1 Parent(s): 0adc84d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -32,17 +32,26 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
35
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | |
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.9 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q2_K.gguf) | i1-Q2_K | 12.9 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.4 | lower quality |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.1 | IQ3_XS probably better |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.8 | IQ3_S probably better |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.6 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.7 | optimal size/speed/quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.8 | fast, recommended |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q6_K.gguf) | i1-Q6_K | 28.3 | practically like static Q6_K |
47
 
48
  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/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.6 | for the desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ2_S.gguf) | i1-IQ2_S | 11.0 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.9 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q2_K.gguf) | i1-Q2_K | 12.9 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.4 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.1 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ3_S.gguf) | i1-IQ3_S | 15.1 | beats Q3_K* |
46
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.7 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.8 | IQ3_S probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.2 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.6 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q4_0.gguf) | i1-Q4_0 | 19.6 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.7 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.8 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.8 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.4 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Yislerp6-34B-i1-GGUF/resolve/main/Yislerp6-34B.i1-Q6_K.gguf) | i1-Q6_K | 28.3 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant