Hugging Face's logo

mradermacher
/
Xinyuan-VL-2B-i1-GGUF

Transformers
GGUF
English
Chinese
multimodal
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
25bcaab
·
verified ·
1 Parent(s): 09c0fb5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -48,9 +48,11 @@ more details, including on how to concatenate multi-part files.
48
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended |
 
54
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | practically like static Q6_K |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS |
52
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended |
55
+ | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Xinyuan-VL-2B-i1-GGUF/resolve/main/Xinyuan-VL-2B.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | practically like static Q6_K |