Hugging Face's logo

mradermacher
/
testrepo-i1-GGUF

Transformers
GGUF
English
Not-For-All-Audiences
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
da0f38f
·
verified ·
1 Parent(s): cf2d609

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -20,7 +20,7 @@ weighted/imatrix quants of https://huggingface.co/nsfwthrowitaway69/Venus-120b-v
20
  **NOT TRUE, THSI IS A TEST REPO WITH FAKE FILES, DO NOT USE**
21
 
22
  <!-- provided-files -->
23
- static quants are available at https://huggingface.co/mradermacher/Venus-120b-v1.0-GGUF
24
  ## Usage
25
 
26
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -33,27 +33,27 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 25.3 | for the desperate |
37
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 27.8 | mostly desperate |
38
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 31.9 | |
39
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 35.5 | |
40
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 37.2 | |
41
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 40.5 | |
42
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 44.3 | IQ3_XXS probably better |
43
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 46.3 | lower quality |
44
- | [GGUF](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 49.3 | |
45
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 51.9 | IQ3_XS probably better |
46
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 52.1 | beats Q3_K* |
47
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 53.8 | |
48
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 57.9 | IQ3_S probably better |
49
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 63.1 | IQ3_M probably better |
50
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 64.3 | |
51
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 68.1 | fast, low quality |
52
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 68.4 | optimal size/speed/quality |
53
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 72.2 | fast, recommended |
54
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 82.9 | |
55
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 85.1 | |
56
- | [PART 1](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-120b-v1.0-i1-GGUF/resolve/main/Venus-120b-v1.0.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 98.8 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):
 
20
  **NOT TRUE, THSI IS A TEST REPO WITH FAKE FILES, DO NOT USE**
21
 
22
  <!-- provided-files -->
23
+ static quants are available at https://huggingface.co/mradermacher/testrepo-GGUF
24
  ## Usage
25
 
26
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ1_M.gguf) | i1-IQ1_M | 0.1 | mostly desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ1_S.gguf) | i1-IQ1_S | 0.1 | for the desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ2_XS.gguf,) | i1-IQ2_XS | 0.4 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q2_K.gguf,) | i1-Q2_K | 0.4 | IQ3_XXS probably better |
43
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 0.4 | optimal size/speed/quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality |
46
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 2.6 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 2.6 | beats Q3_K* |
48
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 2.6 | IQ3_M probably better |
49
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 2.6 | IQ3_S probably better |
50
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 2.6 | IQ3_XS probably better |
51
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 8.4 | |
52
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 8.4 | fast, low quality |
53
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 8.4 | fast, recommended |
54
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 19.8 | |
55
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 19.8 | |
56
+ | [PART 1](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/testrepo-i1-GGUF/resolve/main/testrepo.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 40.9 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):