π Model Description
pipeline_tag: image-to-text base_model:
- datalab-to/chandra
These are quantizations of the model Chandra-OCR
Original model: https://huggingface.co/datalab-to/chandra
Try to use the best quality you can run.
For the mmproj, try to use the F32 version as it will produce the best results. F32 > BF16 > F16
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
Chandra-OCR-BF16.gguf
LFS
FP16
|
15.26 GB | Download |
|
Chandra-OCR-F16.gguf
LFS
FP16
|
15.26 GB | Download |
|
Chandra-OCR-IQ3_M.gguf
LFS
Q3
|
3.63 GB | Download |
|
Chandra-OCR-IQ3_S.gguf
LFS
Q3
|
3.53 GB | Download |
|
Chandra-OCR-IQ3_XS.gguf
LFS
Q3
|
3.38 GB | Download |
|
Chandra-OCR-IQ4_NL.gguf
LFS
Q4
|
4.49 GB | Download |
|
Chandra-OCR-IQ4_XS.gguf
LFS
Q4
|
4.28 GB | Download |
|
Chandra-OCR-Q3_K_L.gguf
LFS
Q3
|
4.13 GB | Download |
|
Chandra-OCR-Q3_K_M.gguf
LFS
Q3
|
3.84 GB | Download |
|
Chandra-OCR-Q3_K_S.gguf
LFS
Q3
|
3.51 GB | Download |
|
Chandra-OCR-Q4_K_M.gguf
Recommended
LFS
Q4
|
4.68 GB | Download |
|
Chandra-OCR-Q4_K_S.gguf
LFS
Q4
|
4.47 GB | Download |
|
Chandra-OCR-Q5_K_M.gguf
LFS
Q5
|
5.45 GB | Download |
|
Chandra-OCR-Q5_K_S.gguf
LFS
Q5
|
5.33 GB | Download |
|
Chandra-OCR-Q6_K.gguf
LFS
Q6
|
6.26 GB | Download |
|
Chandra-OCR-Q8_0.gguf
LFS
Q8
|
8.11 GB | Download |
|
mmproj-BF16.gguf
LFS
FP16
|
1.08 GB | Download |
|
mmproj-F16.gguf
LFS
FP16
|
1.08 GB | Download |
|
mmproj-F32.gguf
LFS
|
2.15 GB | Download |