Transformers
GGUF
Japanese
English
Inference Endpoints
imatrix
mradermacher commited on
Commit
13dce56
·
verified ·
1 Parent(s): 3436af8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -45,15 +45,21 @@ more details, including on how to concatenate multi-part files.
45
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.8 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.4 | lower quality |
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.9 | IQ3_XS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ3_M.gguf) | i1-IQ3_M | 7.5 | |
50
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.8 | IQ3_S probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.9 | |
52
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.1 | IQ3_M probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.3 | fast on arm, low quality |
 
 
 
54
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.5 | fast, recommended |
56
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.1 | |
 
57
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | practically like static Q6_K |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
45
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.8 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.4 | lower quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.7 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ3_S.gguf) | i1-IQ3_S | 6.9 | beats Q3_K* |
50
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.9 | IQ3_XS probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ3_M.gguf) | i1-IQ3_M | 7.5 | |
52
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.8 | IQ3_S probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.9 | |
54
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.1 | IQ3_M probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.3 | fast on arm, low quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.3 | fast on arm+i8mm, low quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.3 | fast on arm+sve, low quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_0.gguf) | i1-Q4_0 | 8.3 | fast, low quality |
59
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
60
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.5 | fast, recommended |
61
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.1 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q5_K_M.gguf) | i1-Q5_K_M | 11.0 | |
63
  | [GGUF](https://huggingface.co/mradermacher/qarasu-14B-chat-plus-unleashed-i1-GGUF/resolve/main/qarasu-14B-chat-plus-unleashed.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | practically like static Q6_K |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant