Hugging Face's logo

mradermacher
/
EVA-Instruct-SP-32B-i1-GGUF

Transformers
GGUF
English
chat
Merge
roleplay
Not-For-All-Audiences
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
30c73ad
·
verified ·
1 Parent(s): 15dce98

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -45,7 +45,9 @@ more details, including on how to concatenate multi-part files.
45
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
 
48
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
 
49
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
50
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
@@ -53,6 +55,7 @@ more details, including on how to concatenate multi-part files.
53
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
 
56
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
57
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
58
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
 
45
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
49
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
51
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
52
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
 
55
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
58
+ | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
59
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
60
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
61
  | [GGUF](https://huggingface.co/mradermacher/EVA-Instruct-SP-32B-i1-GGUF/resolve/main/EVA-Instruct-SP-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |