Hugging Face's logo

bartowski
/
Tiger-Gemma-9B-v1-GGUF

Text Generation
GGUF
Inference Endpoints
imatrix
conversational
Model card Files Community
2
bartowski commited on
Commit
55f83c5
•
1 Parent(s): 01cea24

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -1,7 +1,7 @@
 
1
  ---
2
- base_model: TheDrummer/Tiger-Gemma-9B-v1
3
- pipeline_tag: text-generation
4
  quantized_by: bartowski
 
5
  ---
6
 
7
  ## Llamacpp imatrix Quantizations of Tiger-Gemma-9B-v1
@@ -39,6 +39,7 @@ Note that this model does not support a System prompt.
39
  | [Tiger-Gemma-9B-v1-Q4_K_L.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
40
  | [Tiger-Gemma-9B-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for must use cases, *recommended*. |
41
  | [Tiger-Gemma-9B-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. |
 
42
  | [Tiger-Gemma-9B-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
43
  | [Tiger-Gemma-9B-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. |
44
  | [Tiger-Gemma-9B-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. |
@@ -47,7 +48,6 @@ Note that this model does not support a System prompt.
47
  | [Tiger-Gemma-9B-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
48
  | [Tiger-Gemma-9B-v1-Q2_K_L.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
49
  | [Tiger-Gemma-9B-v1-Q2_K.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. |
50
- | [Tiger-Gemma-9B-v1-IQ3_XXS.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ3_XXS.gguf) | IQ3_XXS | 3.80GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
51
  | [Tiger-Gemma-9B-v1-IQ2_M.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ2_M.gguf) | IQ2_M | 3.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
52
 
53
  ## Credits
 
1
+
2
  ---
 
 
3
  quantized_by: bartowski
4
+ pipeline_tag: text-generation
5
  ---
6
 
7
  ## Llamacpp imatrix Quantizations of Tiger-Gemma-9B-v1
 
39
  | [Tiger-Gemma-9B-v1-Q4_K_L.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
40
  | [Tiger-Gemma-9B-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for must use cases, *recommended*. |
41
  | [Tiger-Gemma-9B-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. |
42
+ | [Tiger-Gemma-9B-v1-Q3_K_XL.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q3_K_XL.gguf) | Q3_K_XL | 5.35GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
43
  | [Tiger-Gemma-9B-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
44
  | [Tiger-Gemma-9B-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. |
45
  | [Tiger-Gemma-9B-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. |
 
48
  | [Tiger-Gemma-9B-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
49
  | [Tiger-Gemma-9B-v1-Q2_K_L.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
50
  | [Tiger-Gemma-9B-v1-Q2_K.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. |
 
51
  | [Tiger-Gemma-9B-v1-IQ2_M.gguf](https://huggingface.co/bartowski/Tiger-Gemma-9B-v1-GGUF/blob/main/Tiger-Gemma-9B-v1-IQ2_M.gguf) | IQ2_M | 3.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
52
 
53
  ## Credits