wecos myanmar ocr 8b needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
8B Vision‑Language OCR for Burmese and ancient scripts
wecos-myanmar-ocr-8b is an 8.19‑billion parameter multimodal model optimized for complex Myanmar writing systems. It decodes subjoined consonants, ancient epigraphy, palm‑leaf manuscripts, and low‑contrast scans. The model is instruction‑tuned and licensed under Apache‑2.0.
Good at
- OCR of complex Burmese scripts
- Transcription of ancient epigraphy and palm‑leaf manuscripts
- Robustness to low‑contrast and yellowed scans
Limits
- No support for languages other than Burmese and related scripts
- Requires at least 6.7 GB VRAM at 8 k context
- No audio or text‑only mode specified
Best for
- Digitizing Burmese manuscripts
- Transcribing Pali‑Burmese bilingual texts
- Extracting data from low‑contrast scanned documents
Who it’s for. Developers and researchers working on Myanmar OCR, digital humanities projects, and archival digitization of ancient Burmese inscriptions. The model is suitable for those needing accurate recognition of complex subjoined consonants and ancient script forms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → |
For 8 GB VRAM use the Q4_K_M quantization; the file is 5.03 GB and requires about 6.7 GB VRAM at 8 k context. For larger VRAM budgets, higher‑precision quants are not listed. The estimate is approximate.
What GPU do you need for wecos myanmar ocr 8b?
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: the best quant that fits is Q4_K_M (5.0 GB file, about 6.7 GB in use).
Which wecos myanmar ocr 8b quant should you choose?
Q4_K_M is the usual starting point for wecos myanmar ocr 8b: it balances file size and quality well. Here it is a 5.0 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about wecos myanmar ocr 8b
How much VRAM does wecos myanmar ocr 8b need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 wecos myanmar ocr 8b on an 8 GB GPU?
Yes, with Q4_K_M: the 5.0 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of wecos myanmar ocr 8b GGUF?
It depends on the quant: Q4_K_M is 5.0 GB.
What context length does wecos myanmar ocr 8b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download wecos myanmar ocr 8b GGUF?
The files are on Hugging Face in the AKHtun/wecos-myanmar-ocr-8b-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 wecos myanmar ocr 8b 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 this model on 8 GB VRAM?
The Q4_K_M quant requires about 6.7 GB VRAM at 8 k context, so 8 GB is sufficient but close to the limit.
Does it support Pali text?
Yes, it accurately parses interlinear Pali‑Burmese bilingual texts with rare diacritics.
Is the model open source?
Yes, it is distributed under the Apache License 2.0.