Hugging Face's logo

mradermacher
/
gemma2-9b-cpt-sahabatai-v1-instruct-GGUF

Transformers
GGUF
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
b575347
·
verified ·
1 Parent(s): 14c5cd6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -35,7 +35,16 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf) | Q2_K | 3.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
 
 
 
 
 
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
41
  types (lower is better):
 
35
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf) | Q2_K | 3.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf) | IQ4_XS | 5.3 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf) | Q5_K_S | 6.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf) | Q5_K_M | 6.7 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):