Hugging Face's logo

mradermacher
/
Tengentoppa-gemma-2-9b-base-i1-GGUF

Transformers
GGUF
Japanese
imatrix
Model card Files Community
mradermacher commited on
Commit
ccca90e
·
verified ·
1 Parent(s): c2f43df

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -38,15 +38,20 @@ more details, including on how to concatenate multi-part files.
38
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.7 | very low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |
40
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.5 | prefer IQ4_XS |
 
47
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
38
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.7 | very low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |
40
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* |
43
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.5 | prefer IQ4_XS |
49
+ | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q4_1.gguf) | i1-Q4_1 | 6.1 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Tengentoppa-gemma-2-9b-base-i1-GGUF/resolve/main/Tengentoppa-gemma-2-9b-base.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant