mradermacher commited on
Commit
9a92b7a
·
verified ·
1 Parent(s): 85001a9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -1
README.md CHANGED
@@ -33,7 +33,7 @@ static quants of https://huggingface.co/kawasumi/Tema_Q-R12.2
33
 
34
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Tema_Q-R12.2-GGUF).***
35
 
36
- 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.
37
  ## Usage
38
 
39
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -46,7 +46,17 @@ more details, including on how to concatenate multi-part files.
46
 
47
  | Link | Type | Size/GB | Notes |
48
  |:-----|:-----|--------:|:------|
 
 
 
 
49
  | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
 
 
 
 
 
 
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
33
 
34
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Tema_Q-R12.2-GGUF).***
35
 
36
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Tema_Q-R12.2-i1-GGUF
37
  ## Usage
38
 
39
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
46
 
47
  | Link | Type | Size/GB | Notes |
48
  |:-----|:-----|--------:|:------|
49
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q2_K.gguf) | Q2_K | 3.9 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
55
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q5_K_S.gguf) | Q5_K_S | 6.6 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q5_K_M.gguf) | Q5_K_M | 6.7 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):