GL

GLM OCR

GLMGGUF by mradermacherUpdated 2026-10-12
Download on Hugging Face
Parameters891M
Context128K
Layers17
Architectureglm4
Smallest quant0.4 GB
Quick answer

GLM OCR 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 12 quants, from 0.4 GB (Q2_K) to 1.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

GLM OCR – multimodal OCR model with 0.9B parameters

GLM OCR is a 0.9B‑parameter multimodal OCR model built on the GLM‑4 architecture. It uses a CogViT visual encoder and a GLM‑0.5B language decoder to perform layout analysis and text recognition. The model supports high‑quality OCR across complex document layouts.

Good at

  • High‑accuracy OCR on complex tables
  • Fast inference with low latency
  • Robust layout analysis

Limits

  • No vision support in some quant variants
  • Large VRAM needed for higher‑quality quants
  • MIT license only for non‑commercial use

Best for

  • Document parsing pipelines
  • Real‑world business OCR tasks
  • Edge deployment with limited resources

Who it’s for. Developers building OCR services that require accurate text extraction from varied document layouts. The model is suitable for production pipelines needing fast, low‑cost inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.4 GB
Fits Get file →
Q3_K_S0.4 GB 1.5 GB
Fits Get file →
Q3_K_M0.5 GB 1.5 GB
Fits Get file →
Q3_K_L0.5 GB 1.5 GB
Fits Get file →
IQ4_XS0.5 GB 1.6 GB
Fits Get file →
Q4_K_S0.5 GB 1.6 GB
Fits Get file →
Q4_K_M0.5 GB 1.6 GB
Fits Get file →
Q5_K_S0.6 GB 1.7 GB
Fits Get file →
Q5_K_M0.6 GB 1.7 GB
Fits Get file →
Q6_K0.7 GB 1.8 GB
Fits Get file →
Q8_01.0 GB 2.0 GB
Fits Get file →
F161.8 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M or Q4_K_S (≈1.6 GB memory at 8k context). For 12 GB VRAM, Q5_K_M or Q5_K_S (≈1.7 GB). For 16 GB VRAM, Q6_K or Q8_0 (≈1.8–2 GB). Memory estimates are approximate.

What GPU do you need for GLM OCR?

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

Which GLM OCR quant should you choose?

Q4_K_M is the usual starting point for GLM OCR: 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 Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4
Parameters891M
Layers17
Trained context131,072 tokens
KV cache (fp16)68 KB per token

Source

Quantized bymradermacher
FamilyGLM
Base modelzai-org/GLM-OCR
Licensemit
Downloads (HF)4,748
Last updated2026-10-12

Frequently asked questions about GLM OCR

How much VRAM does GLM OCR 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 GLM OCR on an 8 GB GPU?

Yes, with F16: the 1.8 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 GLM OCR GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, IQ4_XS is 0.5 GB, Q4_K_S is 0.5 GB and 6 more.

What context length does GLM OCR 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 GLM OCR GGUF?

The files are on Hugging Face in the mradermacher/GLM-OCR-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 GLM OCR 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 GLM OCR on 8 GB VRAM?

Yes, use Q4_K_M or Q4_K_S quant. They require about 1.6 GB VRAM at 8k context.

Does the model support image input?

Yes, GLM OCR includes vision capabilities via the CogViT encoder.

What license applies to the GGUF files?

The files are released under the MIT license, allowing free use in most projects.

Other GGUFs of GLM-OCR

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More GLM models

All GLM →

Other tiny models

All tiny models →