mradermacher commited on
Commit
46747da
·
verified ·
1 Parent(s): ae2f954

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -58,18 +58,28 @@ more details, including on how to concatenate multi-part files.
58
 
59
  | Link | Type | Size/GB | Notes |
60
  |:-----|:-----|--------:|:------|
 
61
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 27.2 | mostly desperate |
62
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 29.2 | |
 
 
63
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 33.6 | |
64
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q2_K_S.gguf) | i1-Q2_K_S | 33.8 | very low quality |
65
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 34.1 | IQ3_XXS probably better |
66
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 36.4 | lower quality |
 
67
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 39.3 | IQ3_XS probably better |
 
68
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 40.6 | |
69
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 43.1 | IQ3_S probably better |
 
70
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 45.5 | |
 
71
  | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 50.2 | optimal size/speed/quality |
 
72
  | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 54.3 | fast, recommended |
 
 
73
  | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 73.8 | practically like static Q6_K |
74
 
75
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
58
 
59
  | Link | Type | Size/GB | Notes |
60
  |:-----|:-----|--------:|:------|
61
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 26.0 | for the desperate |
62
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 27.2 | mostly desperate |
63
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 29.2 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 31.0 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 32.0 | |
66
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 33.6 | |
67
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q2_K_S.gguf) | i1-Q2_K_S | 33.8 | very low quality |
68
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 34.1 | IQ3_XXS probably better |
69
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 36.4 | lower quality |
70
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 37.5 | |
71
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 39.3 | IQ3_XS probably better |
72
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 39.4 | beats Q3_K* |
73
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 40.6 | |
74
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 43.1 | IQ3_S probably better |
75
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 45.3 | IQ3_M probably better |
76
  | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 45.5 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 47.4 | fast, low quality |
78
  | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 50.2 | optimal size/speed/quality |
79
+ | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_1.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_1.gguf.part2of2) | i1-Q4_1 | 52.4 | |
80
  | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 54.3 | fast, recommended |
81
+ | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 58.9 | |
82
+ | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 62.4 | |
83
  | [PART 1](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Babel-83B-Chat-i1-GGUF/resolve/main/Babel-83B-Chat.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 73.8 | practically like static Q6_K |
84
 
85
  Here is a handy graph by ikawrakow comparing some lower-quality quant