XCurOS OCR needs about 1.6 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
XCurOS OCR – a 0.891B GLM‑4 model for OCR and reasoning
XCurOS OCR is a 0.891 billion‑parameter GLM‑4 model trained on 131 072 tokens. It supports reasoning, tools, and vision. The model is released under the MIT license.
Good at
- OCR tasks
- Reasoning with tools
- Vision integration
Limits
- No vision support in quantized form
- Requires 8 k context for memory estimates
- No mixture of experts
Best for
- OCR in low‑resource environments
- Tool‑augmented reasoning
- Vision‑enabled applications
Who it’s for. Developers building OCR or reasoning applications who need a lightweight, open‑source model. The model is suitable for integration into local LLM pipelines via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.0 GB | 2.0 GB | Fits | Get file → | |
| F16 | 1.8 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.55 GB file, ~1.6 GB memory). If 4 GB VRAM is available, Q3_K_S (0.42 GB file, ~1.5 GB memory) is recommended. For the smallest footprint, Q2_K (0.36 GB file, ~1.4 GB memory) works on 2 GB VRAM.
What GPU do you need for XCurOS OCR?
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: the best quant that fits is F16 (1.8 GB file, about 2.9 GB in use).
Which XCurOS OCR quant should you choose?
Q4_K_M is the usual starting point for XCurOS OCR: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 1.0 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 Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about XCurOS OCR
How much VRAM does XCurOS OCR need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.5 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 XCurOS OCR on an 8 GB GPU?
Yes, with F16: the 1.8 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of XCurOS OCR GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, IQ4_XS is 0.5 GB, Q4_K_S is 0.5 GB and 6 more.
What context length does XCurOS OCR support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download XCurOS OCR GGUF?
The files are on Hugging Face in the mradermacher/XCurOS-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 XCurOS OCR use?
Hugging Face lists the license as mit. 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 XCurOS OCR on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 1.6 GB memory at 8 k context, well within 8 GB VRAM.
Is the model licensed for commercial use?
The model is MIT licensed, allowing commercial use with attribution.
Does the model support vision tasks?
Yes, the model has vision capabilities, but quantized files may not expose them fully.