Hugging Face's logo

mradermacher
/
BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF

Transformers
GGUF
Bulgarian
English
gemma2
instruct
bggpt
insait
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
c048e42
•
1 Parent(s): 570b9b3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -35,19 +35,26 @@ more details, including on how to concatenate multi-part files.
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
 
38
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate |
39
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | |
40
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |
42
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |
46
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
50
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended |
 
 
51
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 6.2 | for the desperate |
39
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate |
40
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 8.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |
44
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* |
48
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |
50
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 15.8 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 19.0 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.5 | |
58
  | [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-27B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-27B-IT-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant