Hugging Face's logo

mradermacher
/
NxCode-SafeCoder-30B-i1-GGUF

Transformers
GGUF
English
code
security
code-repair
oss-bench
Mixture of Experts
chain-of-thought
nlp
c
cpp
php
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
0f87b1a
·
verified ·
1 Parent(s): 5a77f1f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -51,6 +51,8 @@ more details, including on how to concatenate multi-part files.
51
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) |
52
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate |
53
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | |
 
 
54
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | |
55
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better |
@@ -58,9 +60,11 @@ more details, including on how to concatenate multi-part files.
58
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | |
60
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better |
 
61
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | |
62
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality |
63
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended |
 
64
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | practically like static Q6_K |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
51
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) |
52
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate |
53
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | |
56
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | |
57
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality |
58
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better |
 
60
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better |
61
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | |
62
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better |
63
+ | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | |
65
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality |
66
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended |
67
+ | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | |
68
  | [GGUF](https://huggingface.co/mradermacher/NxCode-SafeCoder-30B-i1-GGUF/resolve/main/NxCode-SafeCoder-30B.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | practically like static Q6_K |
69
 
70
  Here is a handy graph by ikawrakow comparing some lower-quality quant