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 8 quants, from 3.8 GB (Q3_K_S) to 32.8 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Chandra OCR model for structured document extraction
Chandra is an OCR model that outputs markdown, HTML, and JSON. It preserves layout and supports over 40 languages. The model is built on qwen3vl architecture with 8.19B parameters.
Good at
- Accurate text extraction from images and PDFs
- Preserves complex layout including tables and math
- Handles handwriting and forms with checkboxes
Limits
- No vision support beyond OCR
- Requires large VRAM for higher quant levels
- OpenRail license limits commercial use
Best for
- Document digitization workflows
- Batch processing of scanned forms
- Generating structured data from PDFs
Who it’s for. Developers needing reliable OCR for multilingual documents. Researchers building document analysis pipelines. Enterprises automating form processing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | 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 → | |
| F32 | 32.8 GB | 34.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (file size 3.77 GB, estimated 5.5 GB memory). For 12 GB VRAM, Q4_K_S (4.8 GB, 6.5 GB memory) is suitable. Higher precision quants like Q8_0 or BF16 require 10–18 GB VRAM and are not recommended for low‑budget setups.
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 Q4_K_M (5.0 GB file, about 6.7 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).
- 32 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
- 48 GB VRAM: the best quant that fits is F32 (32.8 GB file, about 34.5 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 Q3_K_S at 3.8 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 Q4_K_M: the 5.0 GB file needs about 6.7 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: Q3_K_S is 3.8 GB, Q3_K_M is 4.1 GB, Q4_K_S is 4.8 GB, Q4_K_M is 5.0 GB, Q8_0 is 8.7 GB, BF16 is 16.4 GB and 2 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 prithivMLmods/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, the Q3_K_S quant uses about 5.5 GB memory at 8k context, fitting within 8 GB VRAM.
Does Chandra support multiple languages?
Yes, it supports over 40 languages for OCR tasks.