Hugging Face's logo

mradermacher
/
KwaiCoder-23B-A4B-v1-i1-GGUF

Transformers
GGUF
multilingual
code-generation
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
94a98e5
·
verified ·
1 Parent(s): 0151225

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -32,19 +32,28 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
35
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 7.9 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.5 | |
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf) | i1-Q2_K | 9.6 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.6 | very low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.3 | lower quality |
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 11.1 | IQ3_XS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 11.3 | |
43
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.1 | IQ3_S probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.7 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.2 | optimal size/speed/quality |
 
47
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.5 | fast, recommended |
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf) | i1-Q6_K | 20.9 | practically like static Q6_K |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 7.5 | for the desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 7.9 | mostly desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.0 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 9.0 | |
40
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |
41
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q2_K.gguf) | i1-Q2_K | 9.6 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.6 | very low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.3 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.6 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 11.1 | beats Q3_K* |
46
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 11.1 | IQ3_XS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 11.3 | |
48
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.1 | IQ3_S probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.7 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_0.gguf) | i1-Q4_0 | 13.3 | fast, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.2 | optimal size/speed/quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_1.gguf) | i1-Q4_1 | 14.7 | |
54
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.5 | fast, recommended |
55
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.6 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.7 | |
57
  | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-23B-A4B-v1-i1-GGUF/resolve/main/KwaiCoder-23B-A4B-v1.i1-Q6_K.gguf) | i1-Q6_K | 20.9 | practically like static Q6_K |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant