Dharma OCR LITE Bf16 needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.8 GB (IQ4_NL) to 6.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
Dharma OCR LITE Bf16 is a 3.09B-parameter Dharma model in GGUF format, quantized by igorfk369. Its trained context length is 125K tokens. The repository has 6 quant files, from 1.8 GB (IQ4_NL) to 6.2 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 6.2 GB | 7.0 GB | Fits | Get file → |
What GPU do you need for Dharma OCR LITE Bf16?
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 Q6_K (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.2 GB file, about 7.0 GB in use).
Which Dharma OCR LITE Bf16 quant should you choose?
Q4_K_M is the usual starting point for Dharma OCR LITE Bf16: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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 IQ4_NL at 1.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Dharma OCR LITE Bf16
How much VRAM does Dharma OCR LITE Bf16 need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Dharma OCR LITE Bf16 on an 8 GB GPU?
Yes, with BF16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Dharma OCR LITE Bf16 GGUF?
It depends on the quant: IQ4_NL is 1.8 GB, Q4_K_M is 1.9 GB, Q5_K_M is 2.2 GB, Q6_K is 2.5 GB, Q8_0 is 3.3 GB, BF16 is 6.2 GB.
What context length does Dharma OCR LITE Bf16 support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download Dharma OCR LITE Bf16 GGUF?
The files are on Hugging Face in the igorfk369/Dharma-OCR-LITE-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 Dharma OCR LITE Bf16 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.