Hugging Face's logo

mradermacher
/
Gemma-SEA-LION-v4-27B-VL-i1-GGUF

Transformers
GGUF
mergekit
Merge
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
ede139b
·
verified ·
1 Parent(s): 8b54be6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -55,19 +55,28 @@ more details, including on how to concatenate multi-part files.
55
  | Link | Type | Size/GB | Notes |
56
  |:-----|:-----|--------:|:------|
57
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
58
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ1_M.gguf) | i1-IQ1_M | 6.9 | mostly desperate |
59
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.8 | |
 
 
60
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ2_M.gguf) | i1-IQ2_M | 9.6 | |
61
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.9 | very low quality |
62
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q2_K.gguf) | i1-Q2_K | 10.6 | IQ3_XXS probably better |
63
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.8 | lower quality |
 
 
64
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
65
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |
66
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |
67
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |
68
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |
 
69
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
70
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.6 | fast, recommended |
 
 
 
71
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K |
72
 
73
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
55
  | Link | Type | Size/GB | Notes |
56
  |:-----|:-----|--------:|:------|
57
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
58
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ1_S.gguf) | i1-IQ1_S | 6.4 | for the desperate |
59
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ1_M.gguf) | i1-IQ1_M | 6.9 | mostly desperate |
60
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.8 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ2_S.gguf) | i1-IQ2_S | 8.9 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ2_M.gguf) | i1-IQ2_M | 9.6 | |
64
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.9 | very low quality |
65
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q2_K.gguf) | i1-Q2_K | 10.6 | IQ3_XXS probably better |
66
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.8 | lower quality |
67
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* |
69
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
70
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |
71
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |
72
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |
73
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q4_0.gguf) | i1-Q4_0 | 15.7 | fast, low quality |
75
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
76
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.6 | fast, recommended |
77
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q4_1.gguf) | i1-Q4_1 | 17.3 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q5_K_S.gguf) | i1-Q5_K_S | 18.9 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.4 | |
80
  | [GGUF](https://huggingface.co/mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF/resolve/main/Gemma-SEA-LION-v4-27B-VL.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K |
81
 
82
  Here is a handy graph by ikawrakow comparing some lower-quality quant