mradermacher commited on
Commit
cd573fc
·
verified ·
1 Parent(s): 47c3070

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -25,7 +25,7 @@ tags:
25
  static quants of https://huggingface.co/qingy2024/QwQ-14B-Math-v0.2
26
 
27
  <!-- provided-files -->
28
- 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.
29
  ## Usage
30
 
31
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -41,7 +41,14 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q2_K.gguf) | Q2_K | 5.9 | |
42
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
 
 
 
 
 
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
 
25
  static quants of https://huggingface.co/qingy2024/QwQ-14B-Math-v0.2
26
 
27
  <!-- provided-files -->
28
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-i1-GGUF
29
  ## Usage
30
 
31
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
41
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q2_K.gguf) | Q2_K | 5.9 | |
42
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
46
  | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-14B-Math-v0.2-GGUF/resolve/main/QwQ-14B-Math-v0.2.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):