mradermacher commited on
Commit
f47fb6a
·
verified ·
1 Parent(s): c3e20d9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -35,7 +35,7 @@ static quants of https://huggingface.co/numind/NuMarkdown-8B-Thinking
35
 
36
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NuMarkdown-8B-Thinking-GGUF).***
37
 
38
- 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.
39
  ## Usage
40
 
41
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -53,7 +53,15 @@ more details, including on how to concatenate multi-part files.
53
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q2_K.gguf) | Q2_K | 3.1 | |
54
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
55
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
 
 
56
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
 
 
 
 
 
 
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):
 
35
 
36
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NuMarkdown-8B-Thinking-GGUF).***
37
 
38
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-i1-GGUF
39
  ## Usage
40
 
41
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
53
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q2_K.gguf) | Q2_K | 3.1 | |
54
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
55
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
58
  | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
59
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
60
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
64
+ | [GGUF](https://huggingface.co/mradermacher/NuMarkdown-8B-Thinking-GGUF/resolve/main/NuMarkdown-8B-Thinking.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant
67
  types (lower is better):