financeocr models needs about 1.6 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 21 quants, from 0.5 GB (Q4_0) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
FinanceOCR models: a 0.891B GLM4 LLM for finance tasks
FinanceOCR models are built on the GLM4 architecture with 0.891B parameters. The models support reasoning, tools, and vision. They are released under the MIT license and trained on a 131072 token context window.
Good at
- Finance document understanding
- Multimodal reasoning
- Tool integration
Limits
- No vision support beyond basic OCR
- Limited to 131072 token context
- MIT license restricts commercial use without attribution
Best for
- Automated invoice processing
- Financial report summarization
- Chatbot assistance for finance queries
Who it’s for. Developers building finance applications that require multimodal understanding and tool usage. Ideal for teams needing a lightweight, open‑source LLM for document analysis.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.5 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.6 GB | Fits | Get file → | |
| Q5_0 | 0.6 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.2 GB | Fits | Get file → | |
| Q5_0 | 1.2 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.5 GB | Fits | Get file → | |
| F16 | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q5_0 | 2.2 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.4 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.5 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.2 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_0 (0.53 GB) or Q4_K_M (0.55 GB) which need about 1.6 GB memory at 8 k context. For 12 GB VRAM, Q5_0 (0.63 GB) or Q5_K_M (0.64 GB) are suitable, requiring roughly 1.7 GB memory. Higher precision F16 variants need 2–7.2 GB memory and are best on 16 GB+ VRAM.
What GPU do you need for financeocr models?
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 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.2 GB in use).
Which financeocr models quant should you choose?
Q4_K_M is the usual starting point for financeocr models: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 1.0 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 Q4_0 at 0.5 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 financeocr models
How much VRAM does financeocr models need?
About 1.6 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 financeocr models on an 8 GB GPU?
Yes, with F16: the 6.2 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of financeocr models GGUF?
It depends on the quant: Q4_0 is 0.5 GB, Q4_K_M is 0.5 GB, Q5_0 is 0.6 GB, Q5_K_M is 0.6 GB, Q6_K is 0.7 GB, Q8_0 is 1.0 GB and 15 more.
What context length does financeocr models support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download financeocr models GGUF?
The files are on Hugging Face in the Sevilze/financeocr-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does financeocr models 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 FinanceOCR models on 8 GB VRAM?
Yes, the Q4_0 and Q4_K_M quantizations fit within 8 GB VRAM, using about 1.6 GB memory at 8 k context.
Does the model support vision tasks?
The model has basic vision capabilities for OCR but is not designed for complex image understanding.
Is the model free to use in commercial products?
It is MIT licensed, so it can be used commercially with attribution.