Hugging Face's logo

mradermacher
/
HelpingAI2.5-10B-GGUF

Transformers
GGUF
English
HelpingAI
Emotionally-Intelligent
EQ-focused
Conversational
SLM
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
d872d61
•
1 Parent(s): 6500043

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -41,7 +41,15 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q3_K_L.gguf) | Q3_K_L | 5.6 | |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q4_K_S.gguf) | Q4_K_S | 6.0 | fast, recommended |
 
 
 
 
 
 
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
 
41
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q3_K_L.gguf) | Q3_K_L | 5.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.IQ4_XS.gguf) | IQ4_XS | 5.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q4_0_4_4.gguf) | Q4_0_4_4 | 6.0 | fast on arm, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q4_K_S.gguf) | Q4_K_S | 6.0 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q5_K_S.gguf) | Q5_K_S | 7.2 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q5_K_M.gguf) | Q5_K_M | 7.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q6_K.gguf) | Q6_K | 8.5 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.Q8_0.gguf) | Q8_0 | 11.0 | fast, best quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/HelpingAI2.5-10B-GGUF/resolve/main/HelpingAI2.5-10B.f16.gguf) | f16 | 20.5 | 16 bpw, overkill |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):