InferenceIllusionist commited on
Commit
caed7e5
·
verified ·
1 Parent(s): 5a0a711

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -39,16 +39,16 @@ Please note importance matrix quantizations are a work in progress, IQ3 and abov
39
  <b>Tip:</b> Pick a size that can fit in your GPU while still allowing some room for context for best speed from the table below. You may need to pad this further depending on if you are running image gen or TTS as well.
40
  | Quant | Size (GB) | Comments |
41
  |:-----|--------:|:------|
42
- | [IQ2_S](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 14.1 | Better quality than Q3_K_L and below |
43
- | [IQ3_XXS](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 18.2 | Better quality than Q3_K_L and below |
44
- | [IQ3_XS](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 19.3 | Better quality than Q3_K_L and below |
45
- | [IQ3_S](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 20.4 | Better quality than Q3_K_L and below |
46
- | [IQ3_M](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 21.4 | Better quality than Q3_K_L and below |
47
  | [IQ4_XS](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 25.1 | Better quality than Q3_K_L and below |
48
- | [Q4_K_M](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 28.4 | Better quality than Q3_K_L and below |
49
- | [Q5_K_M](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 33.2 | Better quality than Q3_K_L and below |
50
- | [Q6_K](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 38.4 | Better quality than Q3_K_L and below |
51
- | [Q8 0](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-Q4_K_M.gguf) | 49.6 | |
52
 
53
 
54
 
 
39
  <b>Tip:</b> Pick a size that can fit in your GPU while still allowing some room for context for best speed from the table below. You may need to pad this further depending on if you are running image gen or TTS as well.
40
  | Quant | Size (GB) | Comments |
41
  |:-----|--------:|:------|
42
+ | [IQ2_S](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ2_S.gguf) | 14.1 | |
43
+ | [IQ3_XXS](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ3_XXS.gguf) | 18.2 | |
44
+ | [IQ3_XS](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ3_XS.gguf) | 19.3 | |
45
+ | [IQ3_S](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ3_S.gguf) | 20.4 | |
46
+ | [IQ3_M](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ3_M.gguf) | 21.4 | |
47
  | [IQ4_XS](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-IQ4_XS.gguf) | 25.1 | Better quality than Q3_K_L and below |
48
+ | [Q4_K_M](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-Q4_K_M.gguf) | 28.4 | |
49
+ | [Q5_K_M](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-Q5_K_M.gguf) | 33.2 | |
50
+ | [Q6_K](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-Q6_K_XS.gguf) | 38.4 | |
51
+ | [Q8_0](https://huggingface.co/Quant-Cartel/Phainesthesia-8x7b-iMat-GGUF/blob/main/Phainesthesia-1.0-8x7b-iMat-Q8_0.gguf) | 49.6 | |
52
 
53
 
54