Hugging Face's logo

mradermacher
/
Phind-Codefuse-34B-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
Phind/Phind-CodeLlama-34B-v2
codefuse-ai/CodeFuse-CodeLlama-34B
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
ad27b4f
•
1 Parent(s): 5927b7b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -40,14 +40,13 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.IQ4_XS.gguf) | IQ4_XS | 18.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q4_0.gguf) | Q4_0 | 19.5 | fast, low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q4_K_S.gguf) | Q4_K_S | 19.6 | fast, recommended |
43
- | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.IQ4_NL.gguf) | IQ4_NL | 19.6 | slightly worse than Q4_K_S |
44
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q4_K_M.gguf) | Q4_K_M | 20.6 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q5_K_S.gguf) | Q5_K_S | 23.6 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q5_K_M.gguf) | Q5_K_M | 24.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q6_K.gguf) | Q6_K | 28.1 | very good quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q8_0.gguf) | Q8_0 | 36.2 | fast, best quality |
49
 
50
-
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
53
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.IQ4_XS.gguf) | IQ4_XS | 18.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q4_0.gguf) | Q4_0 | 19.5 | fast, low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q4_K_S.gguf) | Q4_K_S | 19.6 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.IQ4_NL.gguf) | IQ4_NL | 19.6 | prefer IQ4_XS |
44
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q4_K_M.gguf) | Q4_K_M | 20.6 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q5_K_S.gguf) | Q5_K_S | 23.6 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q5_K_M.gguf) | Q5_K_M | 24.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q6_K.gguf) | Q6_K | 28.1 | very good quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Phind-Codefuse-34B-GGUF/resolve/main/Phind-Codefuse-34B.Q8_0.gguf) | Q8_0 | 36.2 | fast, best quality |
49
 
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
52