Hugging Face's logo

mradermacher
/
BigWeave-v28-96b-i1-GGUF

Transformers
GGUF
English
Merge
frankenmerge
95b
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
ff7a2fe
·
verified ·
1 Parent(s): 20afc80

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -33,18 +33,25 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
 
36
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ1_M.gguf) | i1-IQ1_M | 22.3 | mostly desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 25.6 | |
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ2_M.gguf) | i1-IQ2_M | 32.5 | |
39
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q2_K.gguf) | i1-Q2_K | 35.5 | IQ3_XXS probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 37.1 | lower quality |
 
41
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 41.6 | IQ3_XS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ3_M.gguf) | i1-IQ3_M | 43.2 | |
43
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 46.4 | IQ3_S probably better |
44
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 50.6 | IQ3_M probably better |
45
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 51.5 | |
 
46
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 54.8 | optimal size/speed/quality |
47
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 57.9 | fast, recommended |
 
 
48
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 79.1 | practically like static Q6_K |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ1_S.gguf) | i1-IQ1_S | 20.3 | for the desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ1_M.gguf) | i1-IQ1_M | 22.3 | mostly desperate |
38
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 25.6 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 28.5 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ2_S.gguf) | i1-IQ2_S | 29.9 | |
41
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ2_M.gguf) | i1-IQ2_M | 32.5 | |
42
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q2_K.gguf) | i1-Q2_K | 35.5 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 37.1 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 39.5 | |
45
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 41.6 | IQ3_XS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ3_M.gguf) | i1-IQ3_M | 43.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 46.4 | IQ3_S probably better |
48
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 50.6 | IQ3_M probably better |
49
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 51.5 | |
50
+ | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 54.6 | fast, low quality |
51
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 54.8 | optimal size/speed/quality |
52
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 57.9 | fast, recommended |
53
+ | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 66.4 | |
54
+ | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 68.2 | |
55
  | [PART 1](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v28-96b-i1-GGUF/resolve/main/BigWeave-v28-96b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 79.1 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant