amad vlm6 needs about 9.1 GB of memory at Q8_0 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Amad VLM6 – Arabic OCR fine‑tuned Qwen2VL model
Amad VLM6 is a Qwen2VL 7.62 b model fine‑tuned for Arabic OCR. It merges two Arabic OCR fine‑tunes of Qwen2.5‑VL‑7B‑Instruct. The model supports vision and requires the mmproj vision encoder.
Good at
- Arabic OCR on dense pages
- High‑quality transcription with 4,096 new tokens
- Vision‑enabled instruction following
Limits
- Reading regresses on 10 of 13 datasets
- Over‑generation on presentation‑slide and muharaf styles
- Requires mmproj file
Best for
- Transcribing Arabic documents
- OCR for Arabic research papers
- Batch processing of Arabic PDFs
Who it’s for. Developers and researchers working with Arabic OCR who need a vision‑enabled model. The model is suitable for applications that can handle its specific over‑generation behavior and require the mmproj file.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → |
The only available quant is Q8_0 with a file size of 8.1 GB. It requires approximately 9.1 GB of VRAM at 8,000‑token context. For systems with 8 GB VRAM, it is not feasible; a larger GPU is needed.
What GPU do you need for amad vlm6?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
Which amad vlm6 quant should you choose?
Q8_0 (8.1 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 amad vlm6
How much VRAM does amad vlm6 need?
About 9.1 GB at Q8_0 with an 8K context window. That is the 8.1 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 amad vlm6 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of amad vlm6 GGUF?
It depends on the quant: Q8_0 is 8.1 GB.
What context length does amad vlm6 support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download amad vlm6 GGUF?
The files are on Hugging Face in the amad-iq/amad-vlm6-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 amad vlm6 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 Amad VLM6 on 8 GB VRAM?
No. The Q8_0 quant requires about 9.1 GB of VRAM at 8,000‑token context, exceeding an 8 GB limit.
Do I need a separate vision encoder?
Yes. The mmproj file is required alongside the model file to provide the vision encoder.
What context length should I use?
Set the context to at least 8,192 tokens and allow up to 4,096 new tokens for output.