mradermacher commited on
Commit
609bfcc
1 Parent(s): 204058c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -32,6 +32,7 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
35
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
@@ -39,14 +40,21 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
40
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
 
42
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
 
43
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
44
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
 
 
 
 
47
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
38
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
41
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
44
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
46
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
47
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.6 | fast on arm, low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
56
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
58
  | [GGUF](https://huggingface.co/mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF/resolve/main/AgoraMix-14B-stock-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant