Hugging Face's logo

mradermacher
/
Yiff-34B-32K-v1b-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
c6350e7
·
verified ·
1 Parent(s): 8cc05b8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -28,27 +28,27 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ1_S.gguf) | i1-IQ1_S | 7.6 | for the desperate |
32
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
33
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | |
34
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.4 | |
35
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ2_S.gguf) | i1-IQ2_S | 11.0 | |
36
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ2_M.gguf) | i1-IQ2_M | 11.9 | |
37
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.4 | lower quality |
38
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.3 | |
39
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.1 | IQ3_XS probably better |
40
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ3_S.gguf) | i1-IQ3_S | 15.1 | beats Q3_K* |
41
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ3_M.gguf) | i1-IQ3_M | 15.7 | |
42
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.8 | IQ3_S probably better |
43
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.2 | IQ3_M probably better |
44
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.6 | |
45
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q4_0.gguf) | i1-Q4_0 | 19.6 | fast, low quality |
46
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.8 | fast, recommended |
47
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.8 | |
48
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.4 | |
49
- | [PART 1](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q2_K.gguf) | i1-Q2_K | 25.8 | IQ3_XXS probably better |
50
- | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q6_K.gguf) | i1-Q6_K | 28.3 | practically like static Q6_K |
51
- | [PART 1](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/.i1-Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ1_S.gguf) | i1-IQ1_S | 7.6 | for the desperate |
32
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.4 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ2_S.gguf) | i1-IQ2_S | 11.0 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ2_M.gguf) | i1-IQ2_M | 11.9 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q2_K.gguf) | i1-Q2_K | 12.9 | IQ3_XXS probably better |
38
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.4 | lower quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.3 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.1 | IQ3_XS probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ3_S.gguf) | i1-IQ3_S | 15.1 | beats Q3_K* |
42
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ3_M.gguf) | i1-IQ3_M | 15.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.8 | IQ3_S probably better |
44
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.2 | IQ3_M probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.6 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q4_0.gguf) | i1-Q4_0 | 19.6 | fast, low quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.7 | optimal size/speed/quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.8 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.8 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.4 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Yiff-34B-32K-v1b-i1-GGUF/resolve/main/Yiff-34B-32K-v1b.i1-Q6_K.gguf) | i1-Q6_K | 28.3 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):