LFM2 350M Extract needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.2 GB (Q4_0) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
LFM2 350M Extract – document‑to‑structured‑data model
LFM2 350M Extract is a 0.354 billion‑parameter model trained to pull key information from unstructured documents into JSON, XML, or YAML. It supports English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, and Spanish. Greedy decoding with temperature = 0 is recommended.
Good at
- Extracting structured data from invoices
- Converting regulatory filings to XML
- Populating knowledge graphs from reports
Limits
- Single‑turn conversations only
- No vision support
- Requires 8 k context for memory estimates
Best for
- Invoice data extraction
- Compliance document conversion
- Analytics pipeline preparation
Who it’s for. Developers building document‑processing pipelines or data‑engineering workflows that need structured outputs from varied text sources. Suitable for teams working with multilingual documents and requiring JSON, XML, or YAML formats.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.4 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM use Q4_0 or Q4_K_M (0.22 GB or 0.23 GB). For 16 GB VRAM Q5_K_M or Q6_K (0.26 GB or 0.29 GB). For 32 GB VRAM use Q8_0 (0.38 GB) or F16 (0.71 GB). Memory estimates are approximate.
What GPU do you need for LFM2 350M Extract?
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 F16 (0.7 GB file, about 1.7 GB in use).
Which LFM2 350M Extract quant should you choose?
Q4_K_M is the usual starting point for LFM2 350M Extract: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 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 0.2 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 LFM2 350M Extract
How much VRAM does LFM2 350M Extract need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 LFM2 350M Extract on an 8 GB GPU?
Yes, with F16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 350M Extract GGUF?
It depends on the quant: Q4_0 is 0.2 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB, F16 is 0.7 GB.
What context length does LFM2 350M Extract support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download LFM2 350M Extract GGUF?
The files are on Hugging Face in the LiquidAI/LFM2-350M-Extract-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 LFM2 350M Extract 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.
Can I run LFM2 350M Extract on 8 GB VRAM?
Yes, using Q4_0 or Q4_K_M quantizations, which are 0.22 GB and 0.23 GB respectively.
Does the model support image inputs?
No, the model does not support vision inputs.
What context length is required for inference?
The model was trained with 128000 tokens and uses 8 k context for memory estimates.