mradermacher commited on
Commit
18b5077
·
verified ·
1 Parent(s): 5bebb64

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -44,21 +44,27 @@ more details, including on how to concatenate multi-part files.
44
 
45
  | Link | Type | Size/GB | Notes |
46
  |:-----|:-----|--------:|:------|
 
47
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ1_M.gguf) | i1-IQ1_M | 26.0 | mostly desperate |
48
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 29.9 | |
49
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 33.1 | |
50
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_S.gguf) | i1-IQ2_S | 34.4 | |
51
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_M.gguf) | i1-IQ2_M | 37.5 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q2_K.gguf) | i1-Q2_K | 41.3 | IQ3_XXS probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 43.2 | lower quality |
 
 
54
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 48.6 | IQ3_XS probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ3_M.gguf) | i1-IQ3_M | 49.8 | |
56
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 53.8 | IQ3_S probably better |
57
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 58.2 | IQ3_M probably better |
58
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 59.7 | |
 
59
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 63.6 | optimal size/speed/quality |
60
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 67.3 | fast, recommended |
61
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 76.7 | |
 
62
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 91.3 | practically like static Q6_K |
63
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
44
 
45
  | Link | Type | Size/GB | Notes |
46
  |:-----|:-----|--------:|:------|
47
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ1_S.gguf) | i1-IQ1_S | 23.7 | for the desperate |
48
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ1_M.gguf) | i1-IQ1_M | 26.0 | mostly desperate |
49
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 29.9 | |
50
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 33.1 | |
51
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_S.gguf) | i1-IQ2_S | 34.4 | |
52
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ2_M.gguf) | i1-IQ2_M | 37.5 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 38.4 | very low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q2_K.gguf) | i1-Q2_K | 41.3 | IQ3_XXS probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 43.2 | lower quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 46.0 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ3_S.gguf) | i1-IQ3_S | 48.6 | beats Q3_K* |
58
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 48.6 | IQ3_XS probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ3_M.gguf) | i1-IQ3_M | 49.8 | |
60
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 53.8 | IQ3_S probably better |
61
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 58.2 | IQ3_M probably better |
62
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 59.7 | |
63
+ | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 63.2 | fast, low quality |
64
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 63.6 | optimal size/speed/quality |
65
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 67.3 | fast, recommended |
66
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 76.7 | |
67
+ | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 78.9 | |
68
  | [PART 1](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-110b-3.3-i1-GGUF/resolve/main/airoboros-110b-3.3.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 91.3 | practically like static Q6_K |
69
 
70
  Here is a handy graph by ikawrakow comparing some lower-quality quant