Hugging Face's logo

mradermacher
/
Venus-103b-v1.1-i1-GGUF

Transformers
GGUF
English
Not-For-All-Audiences
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
057e43a
•
1 Parent(s): 62ef2ad

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -27,6 +27,7 @@ more details, including on how to concatenate multi-part files.
27
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
28
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
29
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
 
30
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 38.3 | IQ3_XXS probably better |
31
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.6 | fast, lower quality |
32
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 42.4 | |
@@ -35,7 +36,9 @@ more details, including on how to concatenate multi-part files.
35
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.5 | IQ3_M probably better |
36
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
37
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.3 | fast, medium quality |
 
38
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
 
39
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
27
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
28
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
29
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
30
+ | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 35.1 | |
31
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 38.3 | IQ3_XXS probably better |
32
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.6 | fast, lower quality |
33
  | [GGUF](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 42.4 | |
 
36
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.5 | IQ3_M probably better |
37
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
38
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.3 | fast, medium quality |
39
+ | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 71.4 | |
40
  | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Venus-103b-v1.1-i1-GGUF/resolve/main/Venus-103b-v1.1.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 85.1 | practically like static Q6_K |
42
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant