mradermacher commited on
Commit
2e629c1
1 Parent(s): 6dce2c1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -35,7 +35,7 @@ more details, including on how to concatenate multi-part files.
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.3 | for the desperate |
38
- | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.8 | for the desperate |
39
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.7 | |
40
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.4 | |
41
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | |
@@ -49,7 +49,7 @@ more details, including on how to concatenate multi-part files.
49
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.8 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.8 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.1 | |
52
- | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 13.9 | slightly worse than Q4_K_S |
53
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q4_0.gguf) | i1-Q4_0 | 13.9 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.0 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.9 | fast, recommended |
@@ -57,7 +57,6 @@ more details, including on how to concatenate multi-part files.
57
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.4 | |
58
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q6_K.gguf) | i1-Q6_K | 20.1 | practically like static Q6_K |
59
 
60
-
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):
63
 
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.3 | for the desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.8 | mostly desperate |
39
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.7 | |
40
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.4 | |
41
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.8 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.8 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.1 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 13.9 | prefer IQ4_XS |
53
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q4_0.gguf) | i1-Q4_0 | 13.9 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.0 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.9 | fast, recommended |
 
57
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.4 | |
58
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-i1-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.i1-Q6_K.gguf) | i1-Q6_K | 20.1 | practically like static Q6_K |
59
 
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
61
  types (lower is better):
62