LF

LFM2-1.2B-Extract

LfmGGUF by MungertUpdated 2025-10-07
Download on Hugging Face
Parameters1.17B
Context125K
Layers16
Architecturelfm2
Smallest quant0.0 GB
Quick answer

LFM2-1.2B-Extract needs about 2.3 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.0 GB to 2.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LFM2-1.2B-Extract: Extract structured data from unstructured documents

LFM2-1.2B-Extract is a 1.17B parameter model fine‑tuned for document extraction. It outputs JSON, XML, or YAML and supports English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, and Spanish. The model is designed for single‑turn conversations and greedy decoding with temperature=0.

Good at

  • Extracting invoice details into JSON
  • Converting regulatory filings into XML
  • Transforming support tickets into YAML

Limits

  • Single‑turn only
  • No vision support
  • License is other

Best for

  • Document extraction pipelines
  • Compliance data conversion
  • Knowledge graph population

Who it’s for. Developers building extraction tools that need structured outputs from diverse documents. Ideal for edge deployment on CPUs, GPUs, or NPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ3_XXS0.5 GB 2.1 GB
Fits Get file →
IQ3_XS0.5 GB 2.1 GB
Fits Get file →
Q3_K_S0.6 GB 2.2 GB
Fits Get file →
IQ3_M0.6 GB 2.2 GB
Fits Get file →
Q3_K_M0.6 GB 2.2 GB
Fits Get file →
IQ4_NL0.7 GB 2.2 GB
Fits Get file →
IQ4_XS0.7 GB 2.2 GB
Fits Get file →
Q4_K_S0.7 GB 2.3 GB
Fits Get file →
Q4_00.7 GB 2.3 GB
Fits Get file →
Q4_10.7 GB 2.3 GB
Fits Get file →
Q4_K_M0.8 GB 2.3 GB
Fits Get file →
Q5_00.9 GB 2.4 GB
Fits Get file →
Q5_K_M0.9 GB 2.5 GB
Fits Get file →
Q5_10.9 GB 2.5 GB
Fits Get file →
Q6_K_M1.0 GB 2.6 GB
Fits Get file →
Q8_01.2 GB 2.8 GB
Fits Get file →
F161.7 GB 3.2 GB
Fits Get file →
BF162.3 GB 3.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.75 GB, 2.3 GB memory) or Q5_K_M (0.88 GB, 2.5 GB memory). For 4 GB VRAM, use IQ3_XXS (0.53 GB, 2.1 GB memory). Larger VRAM allows Q8_0 (1.25 GB, 2.8 GB memory) or F16 (1.65 GB, 3.2 GB memory).

What GPU do you need for LFM2-1.2B-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 BF16 (2.3 GB file, about 3.9 GB in use).

Which LFM2-1.2B-Extract quant should you choose?

Q4_K_M is the usual starting point for LFM2-1.2B-Extract: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.2 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters1.17B
Layers16
Trained context128,000 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMungert
FamilyLfm
Licenseother
Downloads (HF)744
Last updated2025-10-07

Frequently asked questions about LFM2-1.2B-Extract

How much VRAM does LFM2-1.2B-Extract need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.8 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 LFM2-1.2B-Extract on an 8 GB GPU?

Yes, with BF16: the 2.3 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2-1.2B-Extract GGUF?

It depends on the quant: file is 0.0 GB, IQ3_XXS is 0.5 GB, IQ3_XS is 0.5 GB, Q3_K_S is 0.6 GB, IQ3_M is 0.6 GB, Q3_K_M is 0.6 GB and 13 more.

What context length does LFM2-1.2B-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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download LFM2-1.2B-Extract GGUF?

The files are on Hugging Face in the Mungert/LFM2-1.2B-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 LFM2-1.2B-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 LFM2-1.2B-Extract on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M will fit within 8 GB VRAM with approximate memory usage of 2.3–2.5 GB at 8k context.

Does the model support image inputs?

No, LFM2-1.2B-Extract does not support vision inputs.

What decoding strategy is recommended?

Greedy decoding with temperature=0 is recommended for best extraction accuracy.

Other GGUFs of LFM2-1.2B

Similar models

Browse all →

More from Mungert

All by Mungert →

More Lfm models

All Lfm →

Other tiny models

All tiny models →