mradermacher commited on
Commit
0da2083
·
verified ·
1 Parent(s): ad9e943

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -44,7 +44,7 @@ static quants of https://huggingface.co/DavidAU/Gemma-3-Dark-Horror-4B-it
44
 
45
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-3-Dark-Horror-4B-it-GGUF).***
46
 
47
- 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.
48
  ## Usage
49
 
50
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -59,6 +59,18 @@ more details, including on how to concatenate multi-part files.
59
  |:-----|:-----|--------:|:------|
60
  | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement |
61
  | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement |
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
  Here is a handy graph by ikawrakow comparing some lower-quality quant
64
  types (lower is better):
 
44
 
45
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-3-Dark-Horror-4B-it-GGUF).***
46
 
47
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-i1-GGUF
48
  ## Usage
49
 
50
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
59
  |:-----|:-----|--------:|:------|
60
  | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement |
61
  | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement |
62
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q2_K.gguf) | Q2_K | 1.8 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q3_K_S.gguf) | Q3_K_S | 2.0 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q3_K_L.gguf) | Q3_K_L | 2.3 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.IQ4_XS.gguf) | IQ4_XS | 2.4 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended |
68
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended |
69
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q5_K_S.gguf) | Q5_K_S | 2.9 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q5_K_M.gguf) | Q5_K_M | 2.9 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q6_K.gguf) | Q6_K | 3.3 | very good quality |
72
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality |
73
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-3-Dark-Horror-4B-it-GGUF/resolve/main/Gemma-3-Dark-Horror-4B-it.f16.gguf) | f16 | 7.9 | 16 bpw, overkill |
74
 
75
  Here is a handy graph by ikawrakow comparing some lower-quality quant
76
  types (lower is better):