Hugging Face's logo

mradermacher
/
guanaco-65b-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
248b711
·
verified ·
1 Parent(s): 5213ed0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -23,6 +23,7 @@ more details, including on how to concatenate multi-part files.
23
  | Link | Type | Size/GB | Notes |
24
  |:-----|:-----|--------:|:------|
25
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ1_S.gguf) | i1-IQ1_S | 14.7 | for the desperate |
 
26
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 17.9 | |
27
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ2_XS.gguf) | i1-IQ2_XS | 19.7 | |
28
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ2_S.gguf) | i1-IQ2_S | 21.2 | |
@@ -34,11 +35,14 @@ more details, including on how to concatenate multi-part files.
34
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q3_K_S.gguf) | i1-Q3_K_S | 28.6 | IQ3_XS probably better |
35
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ3_M.gguf) | i1-IQ3_M | 30.2 | |
36
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q3_K_M.gguf) | i1-Q3_K_M | 32.0 | IQ3_S probably better |
 
37
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q3_K_L.gguf) | i1-Q3_K_L | 35.1 | IQ3_M probably better |
 
38
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q4_K_S.gguf) | i1-Q4_K_S | 37.5 | optimal size/speed/quality |
39
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q4_K_M.gguf) | i1-Q4_K_M | 39.8 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q5_K_S.gguf) | i1-Q5_K_S | 45.3 | |
41
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q5_K_M.gguf) | i1-Q5_K_M | 46.6 | |
 
42
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
23
  | Link | Type | Size/GB | Notes |
24
  |:-----|:-----|--------:|:------|
25
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ1_S.gguf) | i1-IQ1_S | 14.7 | for the desperate |
26
+ | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65b.i1-IQ1_M.gguf) | i1-IQ1_M | 15.5 | for the desperate |
27
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 17.9 | |
28
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ2_XS.gguf) | i1-IQ2_XS | 19.7 | |
29
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ2_S.gguf) | i1-IQ2_S | 21.2 | |
 
35
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q3_K_S.gguf) | i1-Q3_K_S | 28.6 | IQ3_XS probably better |
36
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-IQ3_M.gguf) | i1-IQ3_M | 30.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q3_K_M.gguf) | i1-Q3_K_M | 32.0 | IQ3_S probably better |
38
+ | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 34.9 | |
39
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q3_K_L.gguf) | i1-Q3_K_L | 35.1 | IQ3_M probably better |
40
+ | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65b.i1-Q4_0.gguf) | i1-Q4_0 | 37.0 | fast, low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q4_K_S.gguf) | i1-Q4_K_S | 37.5 | optimal size/speed/quality |
42
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q4_K_M.gguf) | i1-Q4_K_M | 39.8 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q5_K_S.gguf) | i1-Q5_K_S | 45.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65B-HF.i1-Q5_K_M.gguf) | i1-Q5_K_M | 46.6 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/guanaco-65b-i1-GGUF/resolve/main/guanaco-65b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 53.7 | practically like static Q6_K |
46
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant