Hugging Face's logo

mradermacher
/
Model_Kinship_1-2-GGUF

Transformers
GGUF
English
Merge
mergekit
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
d972a08
·
verified ·
1 Parent(s): 289695e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -36,9 +36,14 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
36
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Model_Kinship_1-2-GGUF/resolve/main/Model_Kinship_1-2.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):