MangaExpert OCR Qwen3.5 2b 20260820 185447 needs about 2.9 GB of memory at its main file (a 2.0 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 1.6 GB.
MangaExpert OCR Qwen3.5 2b – OCR model with vision support
MangaExpert OCR Qwen3.5 2b is a 1.88 billion‑parameter model from the Qwen family. It is trained for OCR tasks and includes vision capabilities. The model is released under the MIT license.
Good at
- OCR of manga pages
- Vision‑enabled text extraction
- Lightweight 2 billion‑parameter size
Limits
- No explicit language support listed
- Only vision, no other modalities
- Requires 8 k context for full memory estimate
Best for
- Extracting text from scanned manga
- Automating subtitle generation
- Batch OCR of comic panels
Who it’s for. Developers building OCR pipelines for manga or comic content. Researchers needing a vision‑enabled, small‑to‑medium LLM for text extraction tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.0 GB | 2.9 GB | Fits | Get file → |
The only available GGUF file has an unknown quantization and a size of 2.01 GB. It requires approximately 2.9 GB of VRAM at 8 k context. For systems with 4 GB VRAM or more, this file is suitable. No other quantizations are provided.
What GPU do you need for MangaExpert OCR Qwen3.5 2b 20260820 185447?
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 (2.0 GB file, about 2.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MangaExpert OCR Qwen3.5 2b 20260820 185447
How much VRAM does MangaExpert OCR Qwen3.5 2b 20260820 185447 need?
About 2.9 GB at its main file with an 8K context window. That is the 2.0 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 MangaExpert OCR Qwen3.5 2b 20260820 185447 on an 8 GB GPU?
Yes, with the smaller files: the 2.0 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 MangaExpert OCR Qwen3.5 2b 20260820 185447 GGUF?
It depends on the quant: file is 2.0 GB.
What context length does MangaExpert OCR Qwen3.5 2b 20260820 185447 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download MangaExpert OCR Qwen3.5 2b 20260820 185447 GGUF?
The files are on Hugging Face in the The1Just/MangaExpertOCR repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MangaExpert OCR Qwen3.5 2b 20260820 185447 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 this model on 4 GB VRAM?
The model requires about 2.9 GB of VRAM at 8 k context, so 4 GB VRAM should be sufficient.
Does this model support multiple languages?
No language list is provided; the model is generic and not tied to specific languages.
Is vision support included?
Yes, the model has detected vision capabilities.