Hugging Face's logo

mradermacher
/
Phi4-MoE-2x14B-Instruct-GGUF

Transformers
GGUF
English
phi4
phi3
phi
phi-moe
Mixture of Experts
llama
4bit
conversational
Model card Files Community
mradermacher commited on
Commit
aff8072
·
verified ·
1 Parent(s): b44cca5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -41,8 +41,11 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q3_K_S.gguf) | Q3_K_S | 24.4 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q3_K_M.gguf) | Q3_K_M | 24.5 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q3_K_L.gguf) | Q3_K_L | 24.6 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q4_K_S.gguf) | Q4_K_S | 24.8 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q4_K_M.gguf) | Q4_K_M | 24.9 | fast, recommended |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q6_K.gguf) | Q6_K | 25.3 | very good quality |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
41
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q3_K_S.gguf) | Q3_K_S | 24.4 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q3_K_M.gguf) | Q3_K_M | 24.5 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q3_K_L.gguf) | Q3_K_L | 24.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.IQ4_XS.gguf) | IQ4_XS | 24.7 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q4_K_S.gguf) | Q4_K_S | 24.8 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q4_K_M.gguf) | Q4_K_M | 24.9 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q5_K_S.gguf) | Q5_K_S | 25.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q5_K_M.gguf) | Q5_K_M | 25.1 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Phi4-MoE-2x14B-Instruct-GGUF/resolve/main/Phi4-MoE-2x14B-Instruct.Q6_K.gguf) | Q6_K | 25.3 | very good quality |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant