Hugging Face's logo

mradermacher
/
LeoLM-hessianai-7b-chat-GGUF

Transformers
GGUF
English
German
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
3915867
·
verified ·
1 Parent(s): 0acb992

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -40,10 +40,14 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
41
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
41
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
44
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
48
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/LeoLM-hessianai-7b-chat-GGUF/resolve/main/LeoLM-hessianai-7b-chat.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):