Tadpole 0.8B needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.5 GB (Q4_K_M) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Tiny diagram‑reading LLM for converting visual diagrams to structured text
Tadpole 0.8B is a 0.752 billion‑parameter model that extracts boxes, labels and arrows from flowcharts, UML, BPMN and logic circuits. It outputs structured text that can be converted to JSON, YAML or XML. The model is packaged for llama.cpp and runs on CPU or GPU.
Good at
- Diagram OCR
- Structured text conversion
- Low‑resource inference
Limits
- Large context 262144 tokens
- Requires 1.4–2.4 GB VRAM for Q4_K_M to BF16
- No text‑only generation beyond diagram extraction
Best for
- Extracting UML diagrams to code
- Converting BPMN to XML
- Generating structured data from hand‑drawn flowcharts
Who it’s for. Developers and designers who need automated extraction of diagram elements into machine‑readable formats. It is useful for documentation pipelines and visual data processing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.53 GB file, 1.4 GB memory) is ideal. If more memory is available, Q8_0 (0.81 GB file, 1.7 GB memory) offers slightly higher precision. BF16 (1.52 GB file, 2.4 GB memory) is best for maximum accuracy when memory permits.
What GPU do you need for Tadpole 0.8B?
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: the best quant that fits is BF16 (1.5 GB file, about 2.4 GB in use).
Which Tadpole 0.8B quant should you choose?
Q4_K_M is the usual starting point for Tadpole 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Tadpole 0.8B
How much VRAM does Tadpole 0.8B need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Tadpole 0.8B on an 8 GB GPU?
Yes, with BF16: the 1.5 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 Tadpole 0.8B GGUF?
It depends on the quant: Q4_K_M is 0.5 GB, Q8_0 is 0.8 GB, BF16 is 1.5 GB.
What context length does Tadpole 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download Tadpole 0.8B GGUF?
The files are on Hugging Face in the Srinjoy99/tadpole-0.8b-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 Tadpole 0.8B 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 Tadpole 0.8B on 8 GB VRAM?
Yes, all quantizations fit within 8 GB VRAM, with Q4_K_M using 1.4 GB memory.
Does the model support GPU inference?
Yes, it runs on GPU via llama.cpp without requiring Python.
Is Tadpole 0.8B vision capable?
Yes, it reads diagrams and outputs structured text.