Hugging Face's logo

mradermacher
/
BurningBruce-003-i1-GGUF

Transformers
GGUF
English
Merge
Mixture of Experts
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
531980d
·
verified ·
1 Parent(s): aace8de

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -41,14 +41,19 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.3 | very low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q2_K.gguf) | i1-Q2_K | 8.9 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
 
44
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
 
45
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ3_M.gguf) | i1-IQ3_M | 10.7 | |
46
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.7 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.0 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.8 | optimal size/speed/quality |
50
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.7 | fast, recommended |
 
51
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.7 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q6_K.gguf) | i1-Q6_K | 19.9 | practically like static Q6_K |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
41
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.3 | very low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q2_K.gguf) | i1-Q2_K | 8.9 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ3_S.gguf) | i1-IQ3_S | 10.6 | beats Q3_K* |
47
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ3_M.gguf) | i1-IQ3_M | 10.7 | |
48
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.7 | IQ3_S probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.0 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q4_0.gguf) | i1-Q4_0 | 13.8 | fast, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.8 | optimal size/speed/quality |
53
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.7 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q4_1.gguf) | i1-Q4_1 | 15.2 | |
55
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.7 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.2 | |
57
  | [GGUF](https://huggingface.co/mradermacher/BurningBruce-003-i1-GGUF/resolve/main/BurningBruce-003.i1-Q6_K.gguf) | i1-Q6_K | 19.9 | practically like static Q6_K |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant