Hugging Face's logo

mradermacher
/
Qwen2-VL-OCR-2B-Instruct-GGUF

Transformers
GGUF
English
Math
OCR
Latex
VLM
Plain_Text
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b0f8fa6
·
verified ·
1 Parent(s): d2ac811

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -48,6 +48,7 @@ more details, including on how to concatenate multi-part files.
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.f16.gguf) | f16 | 3.2 | 16 bpw, overkill |
53
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | vision supplement |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR-2B-Instruct.f16.gguf) | f16 | 3.2 | 16 bpw, overkill |
54