GLM OCR needs about 2.0 GB of memory at Q8_0 (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.0 GB (Q8_0) to 1.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
GLM OCR – multimodal OCR model for complex document understanding
GLM OCR is a 0.9B parameter multimodal model built on the GLM‑4 architecture. It uses a CogViT visual encoder and a GLM‑0.5B language decoder to perform OCR, layout analysis, and information extraction. The model supports up to 131 072 context tokens and is released under the MIT license.
Good at
- OCR on complex documents
- Layout analysis and table recognition
- High‑quality text extraction
Limits
- No vision support beyond OCR
- Requires 2 GB VRAM for Q8_0 at 8 k context
- No explicit support for other modalities
Best for
- Document digitization pipelines
- Automated form extraction
- Batch OCR processing
Who it’s for. Developers building document‑centric applications or services that need accurate OCR and layout analysis. The model is suitable for production use with its open‑source SDK and lightweight size.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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 the Q8_0 quantization (0.95 GB file, ~2 GB memory at 8 k context). If more VRAM is available, the F16 quant (1.79 GB file, ~2.9 GB memory) offers higher precision. Memory estimates are approximate.
What GPU do you need for GLM 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 GLM OCR quant should you choose?
Q8_0 (1.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM OCR
How much VRAM does GLM OCR need?
About 2.0 GB at Q8_0 with an 8K context window. That is the 1.0 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 GLM 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 GLM OCR GGUF?
It depends on the quant: Q8_0 is 1.0 GB, F16 is 1.8 GB.
What context length does GLM 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 GLM OCR GGUF?
The files are on Hugging Face in the ggml-org/GLM-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 GLM 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 GLM OCR on 8 GB VRAM?
Yes, the Q8_0 quantization requires about 2 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does GLM OCR support other modalities besides vision?
No, the model is designed specifically for OCR and does not support additional modalities.