mradermacher commited on
Commit
8eae706
·
verified ·
1 Parent(s): ff87f1c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -29,7 +29,7 @@ quantized_by: mradermacher
29
  static quants of https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-14B
30
 
31
  <!-- provided-files -->
32
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
33
  ## Usage
34
 
35
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -46,8 +46,13 @@ more details, including on how to concatenate multi-part files.
46
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
 
 
 
50
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
 
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
 
29
  static quants of https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-14B
30
 
31
  <!-- provided-files -->
32
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-i1-GGUF
33
  ## Usage
34
 
35
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
46
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-14B-GGUF/resolve/main/Dumpling-Qwen2.5-14B.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
58
  types (lower is better):