Pepperocr 1 4b needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.1 GB (Q3_K_S) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Pepperocr 1 4b – a 4.21B parameter vision‑language model for document parsing
Pepperocr 1 4b is a 4.21‑billion‑parameter model based on Qwen3.5. It is fine‑tuned for converting document images into Markdown. The model supports reasoning, tools, and vision tasks.
Good at
- Document image to Markdown conversion
- Multilingual document parsing
- Vision‑language reasoning
Limits
- No vision support in llama.cpp
- Requires large VRAM for higher context
- License is Apache‑2.0
Best for
- OCR pipelines
- Document digitization workflows
- Markdown generation from scanned pages
Who it’s for. Developers building OCR or document processing applications who need a lightweight, open‑source model. The model is suitable for research and production environments that can handle its VRAM requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 2.1 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → | |
| F16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM use Q3_K_S (file size 2.07 GB, estimated 3.6 GB memory). For 12 GB VRAM Q4_K_M (2.71 GB, 4.3 GB memory) offers a balance of size and quality. For 16 GB VRAM or higher, Q8_0 (4.48 GB, 6.1 GB memory) provides full precision.
What GPU do you need for Pepperocr 1 4b?
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 Q3_K_L (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which Pepperocr 1 4b quant should you choose?
Q4_K_M is the usual starting point for Pepperocr 1 4b: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 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 Q3_K_S at 2.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Pepperocr 1 4b
How much VRAM does Pepperocr 1 4b need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Pepperocr 1 4b on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Pepperocr 1 4b GGUF?
It depends on the quant: Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_S is 3.0 GB and 4 more.
What context length does Pepperocr 1 4b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Pepperocr 1 4b GGUF?
The files are on Hugging Face in the prithivMLmods/pepperocr-1-4b-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 Pepperocr 1 4b 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 Pepperocr 1 4b on 8 GB VRAM?
Yes, using the Q3_K_S quantization which estimates 3.6 GB VRAM usage at 8k context.
Does the model support vision tasks in llama.cpp?
No, the model’s vision capabilities are not available in llama.cpp.
What license applies to Pepperocr 1 4b?
The model is released under the Apache‑2.0 license.