Chandra needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 16 quants, from 3.6 GB (IQ3_XS) to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Chandra OCR model for accurate text extraction
Chandra is an OCR model that outputs markdown, HTML, and JSON. It preserves layout, supports handwriting, tables, math, and complex forms. The model supports 40+ languages.
Good at
- Accurate OCR with layout preservation
- Handwriting and table extraction
- Multi‑language support
Limits
- No vision support beyond OCR
- Requires 8k context for estimates
- OpenRail license restricts commercial use
Best for
- Document digitization
- Form reconstruction
- Image‑to‑text conversion
Who it’s for. Developers needing precise OCR output in structured formats. Researchers working on document analysis and data extraction.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| BF16 | 16.4 GB | 18.1 GB | Too big | Get file → | |
| F16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_XS (3.63 GB, 5.3 GB memory) or Q3_K_S (3.77 GB, 5.5 GB memory). If 12 GB VRAM is available, Q4_K_M (5.03 GB, 6.7 GB memory) offers higher quality. For best accuracy, use Q8_0 (8.71 GB, 10.4 GB memory).
What GPU do you need for Chandra?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
Which Chandra quant should you choose?
Q4_K_M is the usual starting point for Chandra: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ3_XS at 3.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Chandra
How much VRAM does Chandra need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Chandra on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Chandra GGUF?
It depends on the quant: IQ3_XS is 3.6 GB, Q3_K_S is 3.8 GB, IQ3_S is 3.8 GB, IQ3_M is 3.9 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.4 GB and 10 more.
What context length does Chandra support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Chandra GGUF?
The files are on Hugging Face in the noctrex/Chandra-OCR-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Chandra use?
Hugging Face lists the license as openrail. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Chandra on 8 GB VRAM?
Yes, use IQ3_XS or Q3_K_S quantizations. They require about 5.3–5.5 GB memory at 8k context.
Does Chandra support images with complex layouts?
Yes, it extracts images, diagrams, and tables with captions and structured data.