Hugging Face's logo

mradermacher
/
Miqu-6B-truthy-GGUF

Transformers
GGUF
English
miqu
conversational
Model card Files Community
mradermacher commited on
Commit
5e74a21
·
verified ·
1 Parent(s): da1796d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -37,9 +37,14 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q3_K_S.gguf) | Q3_K_S | 2.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q3_K_L.gguf) | Q3_K_L | 3.1 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q4_K_S.gguf) | Q4_K_S | 3.4 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q6_K.gguf) | Q6_K | 4.7 | very good quality |
 
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
37
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q3_K_S.gguf) | Q3_K_S | 2.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q3_K_L.gguf) | Q3_K_L | 3.1 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.IQ4_XS.gguf) | IQ4_XS | 3.2 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q4_K_S.gguf) | Q4_K_S | 3.4 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q5_K_S.gguf) | Q5_K_S | 4.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q5_K_M.gguf) | Q5_K_M | 4.1 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q6_K.gguf) | Q6_K | 4.7 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.Q8_0.gguf) | Q8_0 | 6.1 | fast, best quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-6B-truthy-GGUF/resolve/main/Miqu-6B-truthy.f16.gguf) | f16 | 11.4 | 16 bpw, overkill |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):