LI

LightOnOCR 1B 1025

LightonocrGGUF by noctrexUpdated 2025-11-04
Download on Hugging Face
Parameters752M
Context8K
Layers28
Architectureqwen3
Smallest quant0.0 GB
Quick answer

LightOnOCR 1B 1025 needs about 1.9 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 32 quants, from 0.0 GB to 1.5 GB (F16).

LightOnOCR 1B 1025 is a 752M-parameter Lightonocr model in GGUF format, quantized by noctrex. Its trained context length is 8K tokens. The repository has 32 quant files, from 0.0 GB to 1.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ1_S0.3 GB 1.7 GB
Fits Get file →
IQ1_M0.3 GB 1.7 GB
Fits Get file →
IQ2_XXS0.3 GB 1.7 GB
Fits Get file →
IQ2_XS0.3 GB 1.7 GB
Fits Get file →
TQ1_00.3 GB 1.8 GB
Fits Get file →
IQ2_S0.3 GB 1.8 GB
Fits Get file →
Q2_K_S0.3 GB 1.8 GB
Fits Get file →
IQ2_M0.3 GB 1.8 GB
Fits Get file →
TQ2_00.3 GB 1.8 GB
Fits Get file →
IQ3_XXS0.3 GB 1.8 GB
Fits Get file →
Q2_K0.3 GB 1.8 GB
Fits Get file →
IQ3_XS0.4 GB 1.8 GB
Fits Get file →
IQ3_S0.4 GB 1.8 GB
Fits Get file →
Q3_K_S0.4 GB 1.8 GB
Fits Get file →
IQ3_M0.4 GB 1.8 GB
Fits Get file →
Q3_K_M0.4 GB 1.9 GB
Fits Get file →
Q3_K_L0.4 GB 1.9 GB
Fits Get file →
IQ4_XS0.5 GB 1.9 GB
Fits Get file →
IQ4_NL0.5 GB 1.9 GB
Fits Get file →
Q4_00.5 GB 1.9 GB
Fits Get file →
Q4_K_S0.5 GB 1.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
Q4_10.5 GB 1.9 GB
Fits Get file →
Q5_K_S0.5 GB 2.0 GB
Fits Get file →
Q5_00.5 GB 2.0 GB
Fits Get file →
Q5_K_M0.6 GB 2.0 GB
Fits Get file →
Q5_10.6 GB 2.0 GB
Fits Get file →
Q6_K0.6 GB 2.1 GB
Fits Get file →
Q8_00.8 GB 2.2 GB
Fits Get file →
BF161.5 GB 2.9 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →

What GPU do you need for LightOnOCR 1B 1025?

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 (1.5 GB file, about 2.9 GB in use).

Which LightOnOCR 1B 1025 quant should you choose?

Q4_K_M is the usual starting point for LightOnOCR 1B 1025: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 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

Architectureqwen3
Parameters752M
Layers28
Trained context8,192 tokens
KV cache (fp16)112 KB per token

Source

Quantized bynoctrex
Downloads (HF)389
Last updated2025-11-04

Frequently asked questions about LightOnOCR 1B 1025

How much VRAM does LightOnOCR 1B 1025 need?

About 1.9 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 LightOnOCR 1B 1025 on an 8 GB GPU?

Yes, with BF16: the 1.5 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LightOnOCR 1B 1025 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.3 GB, TQ1_0 is 0.3 GB and 26 more.

What context length does LightOnOCR 1B 1025 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.

Where can I download LightOnOCR 1B 1025 GGUF?

The files are on Hugging Face in the noctrex/LightOnOCR-1B-1025-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of LightOnOCR-1B-1025

Similar models

Browse all →

More from noctrex

All by noctrex →

More Lightonocr models

All Lightonocr →

Other tiny models

All tiny models →