Hugging Face's logo

mradermacher
/
KitchenSink_103b-i1-GGUF

Transformers
GGUF
English
rp
erp
chat
storywriting
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
53ab6aa
•
1 Parent(s): 077a883

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -30,7 +30,7 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
33
- | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ1_M.gguf) | i1-IQ1_M | 24.2 | for the desperate |
34
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
35
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ2_S.gguf) | i1-IQ2_S | 32.3 | |
@@ -51,7 +51,6 @@ more details, including on how to concatenate multi-part files.
51
  | [PART 1](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
52
  | [PART 1](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 85.1 | practically like static Q6_K |
53
 
54
-
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):
57
 
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ1_M.gguf) | i1-IQ1_M | 24.2 | mostly desperate |
34
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
35
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-IQ2_S.gguf) | i1-IQ2_S | 32.3 | |
 
51
  | [PART 1](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
52
  | [PART 1](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 85.1 | practically like static Q6_K |
53
 
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56