mradermacher commited on
Commit
ae390f3
·
verified ·
1 Parent(s): ed2893d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -29,11 +29,28 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q2_K.gguf) | i1-Q2_K | 7.2 | IQ3_XXS probably better |
33
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.5 | lower quality |
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.6 | |
35
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.3 | IQ3_S probably better |
 
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.0 | optimal size/speed/quality |
 
 
 
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
39
  types (lower is better):
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.2 | for the desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.6 | mostly desperate |
34
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.2 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.8 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ2_S.gguf) | i1-IQ2_S | 6.0 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.7 | very low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q2_K.gguf) | i1-Q2_K | 7.2 | IQ3_XXS probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.5 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.4 | IQ3_XS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ3_S.gguf) | i1-IQ3_S | 8.4 | beats Q3_K* |
44
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.6 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.3 | IQ3_S probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.1 | IQ3_M probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.4 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q4_0.gguf) | i1-Q4_0 | 11.0 | fast, low quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.0 | optimal size/speed/quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 11.7 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.3 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 13.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_11Bx2_MoE_19B-i1-GGUF/resolve/main/Mixtral_11Bx2_MoE_19B.i1-Q6_K.gguf) | i1-Q6_K | 15.8 | practically like static Q6_K |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):