Hugging Face's logo

mradermacher
/
Code-290k-6.7B-Instruct-GGUF

Transformers
GGUF
English
code
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
bc8cae2
•
1 Parent(s): 4b015c9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -37,9 +37,15 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
 
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
37
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF/resolve/main/Code-290k-6.7B-Instruct.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):