Transformers
GGUF
imatrix
mradermacher commited on
Commit
9618f0a
·
verified ·
1 Parent(s): 7b83c44

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -74,12 +74,21 @@ more details, including on how to concatenate multi-part files.
74
 
75
  | Link | Type | Size/GB | Notes |
76
  |:-----|:-----|--------:|:------|
 
 
 
 
 
77
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 68.2 | IQ3_XXS probably better |
78
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 70.9 | lower quality |
 
79
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 87.4 | |
80
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 94.5 | IQ3_S probably better |
 
81
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 103.1 | optimal size/speed/quality |
 
82
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 114.8 | fast, recommended |
 
83
 
84
  Here is a handy graph by ikawrakow comparing some lower-quality quant
85
  types (lower is better):
 
74
 
75
  | Link | Type | Size/GB | Notes |
76
  |:-----|:-----|--------:|:------|
77
+ | [GGUF](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ1_M.gguf) | i1-IQ1_M | 42.9 | mostly desperate |
78
+ | [GGUF](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 48.8 | |
79
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ2_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ2_XS.gguf.part2of2) | i1-IQ2_XS | 54.0 | |
80
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ2_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ2_M.gguf.part2of2) | i1-IQ2_M | 61.8 | |
81
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q2_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q2_K_S.gguf.part2of2) | i1-Q2_K_S | 62.5 | very low quality |
82
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 68.2 | IQ3_XXS probably better |
83
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 70.9 | lower quality |
84
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 78.8 | IQ3_XS probably better |
85
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 87.4 | |
86
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 94.5 | IQ3_S probably better |
87
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 96.7 | |
88
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 103.1 | optimal size/speed/quality |
89
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_L.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_L.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q3_K_L.gguf.part3of3) | i1-Q3_K_L | 103.1 | IQ3_M probably better |
90
  | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 114.8 | fast, recommended |
91
+ | [PART 1](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloom-i1-GGUF/resolve/main/bloom.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 147.7 | practically like static Q6_K |
92
 
93
  Here is a handy graph by ikawrakow comparing some lower-quality quant
94
  types (lower is better):