Arabic GLM OCR v2 needs about 2.4 GB of memory at its main file (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Arabic GLM OCR v2 – high‑accuracy Arabic OCR in GGUF format
Arabic GLM OCR v2 is a 0.673B GLM4 model converted to GGUF. It supports reasoning, tools, and vision, with a trained context of 131072 tokens. The model is released under the Apache‑2.0 license.
Good at
- Arabic OCR
- Vision‑enabled reasoning
- Tool usage
Limits
- No vision support beyond OCR
- Large memory requirement
- No mixture of experts
Best for
- OCR tasks in Arabic
- Vision‑based Arabic text extraction
- Tool‑augmented Arabic queries
Who it’s for. Developers building Arabic OCR solutions or integrating vision‑enabled language models. The model is suitable for applications requiring accurate Arabic text recognition and reasoning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.4 GB | 2.4 GB | Fits | Get file → |
The single available quant is unknown with a file size of 1.35 GB. It requires approximately 2.4 GB of VRAM at 8 k context. For 8 GB VRAM, it fits comfortably. For 4 GB VRAM, it is too large.
What GPU do you need for Arabic GLM OCR v2?
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 the main file (1.4 GB file, about 2.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Arabic GLM OCR v2
How much VRAM does Arabic GLM OCR v2 need?
About 2.4 GB at its main file with an 8K context window. That is the 1.4 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 Arabic GLM OCR v2 on an 8 GB GPU?
Yes, with the smaller files: the 1.4 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Arabic GLM OCR v2 GGUF?
It depends on the quant: file is 1.4 GB.
What context length does Arabic GLM OCR v2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Arabic GLM OCR v2 GGUF?
The files are on Hugging Face in the Makadi86/Arabic-GLM-OCR-v2-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 Arabic GLM OCR v2 use?
Hugging Face lists the license as apache-2.0. 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 Arabic GLM OCR v2 on 8 GB VRAM?
Yes, the model requires about 2.4 GB of VRAM at 8 k context, fitting within an 8 GB GPU.
Does the model support vision tasks?
Yes, it includes vision capabilities for OCR and related tasks.
What license does the model use?
The model is released under the Apache‑2.0 license.