Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.7 GB (Q2_K) to 3.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Qari OCR 0.3 VL 2B Instruct merged – vision‑language OCR for Arabic
Qari OCR 0.3 VL 2B Instruct merged is a vision‑language model fine‑tuned for Arabic optical character recognition. Built on Qwen2-VL-2B-Instruct, it preserves document layout and HTML tags while transcribing Arabic text. The model supports full diacritics and multi‑font handling.
Good at
- Layout‑aware OCR with HTML tags
- Full Arabic diacritics support
- Multi‑font recognition
Limits
- Context length 32768 tokens
- Requires vision input only
- Apache‑2.0 license
Best for
- Arabic document OCR
- Structural document understanding
- Transcribing scanned PDFs
Who it’s for. Developers building Arabic OCR pipelines or document analysis tools. Researchers needing a vision‑language model for Arabic text extraction.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.7 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.1 GB | 3.8 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (file size 0.99 GB, estimated 1.7 GB memory). For 12 GB VRAM use Q5_K_M (1.13 GB, 1.9 GB memory). For 24 GB VRAM use Q8_0 (1.65 GB, 2.4 GB memory). Estimates are approximate.
What GPU do you need for Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged?
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 (3.1 GB file, about 3.8 GB in use).
Which Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged quant should you choose?
Q4_K_M is the usual starting point for Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 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 0.7 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 Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged
How much VRAM does Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged need?
About 1.7 GB at Q4_K_M 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 Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged on an 8 GB GPU?
Yes, with F16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged GGUF?
It depends on the quant: Q2_K is 0.7 GB, Q3_K_S is 0.8 GB, Q3_K_M is 0.8 GB, Q3_K_L is 0.9 GB, IQ4_XS is 0.9 GB, Q4_K_S is 0.9 GB and 6 more.
What context length does Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged GGUF?
The files are on Hugging Face in the mradermacher/Qari-OCR-0.3-SNAPSHOT-VL-2B-Instruct-merged-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 Qari OCR 0.3 SNAPSHOT VL 2B Instruct merged 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 Qari OCR 0.3 on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 1.7 GB memory at 8 k context, fitting within 8 GB VRAM with headroom.
Does the model support non‑Arabic languages?
No, it is specialized for Arabic OCR and document structure.
What context length does the model support?
The model was trained with 32768 context tokens and can handle that length.