GL

glm ocr crispembed

GLMGGUF by cstrUpdated 2026-08-07
Download on Hugging Face
Parameters1.11B
Context—
Layers—
Architectureglm_ocr_ref
Smallest quant0.0 GB
Quick answer

glm ocr crispembed needs about 0.6 GB of memory at its main file (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.0 GB to 2.6 GB (F16).

GLM-OCR CrispEmbed: 2B‑parameter OCR model in GGUF format

GLM-OCR CrispEmbed is a 1.11‑billion‑parameter vision‑language model converted to GGUF. It builds on GLM‑Edge‑V‑2B with a SigLIP vision encoder and GLM‑4 decoder for OCR tasks. The model is available in several quantizations.

Good at

  • Document OCR
  • Scene text extraction
  • Handwriting recognition

Limits

  • License is GLM‑4 Model Licence, not Apache‑2.0
  • No language list provided
  • Context length not specified

Best for

  • OCR in documents
  • Extracting text from images
  • Handwritten note digitization

Who it’s for. Developers and researchers needing a lightweight OCR model for local inference. The model is suitable for integration into applications that require on‑device text extraction.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.1 GB 0.6 GB
Fits Get file →
—0.1 GB 0.6 GB
Fits Get file →
Q4_K0.9 GB 1.5 GB
Fits Get file →
Q8_01.2 GB 1.8 GB
Fits Get file →
F162.6 GB 3.4 GB
Fits Get file →

For 8‑GB VRAM, use the Q4_K quantization (0.89 GB file, ~1.5 GB memory at 8k context). If more memory is available, Q8_0 (1.18 GB, ~1.8 GB) or F16 (2.58 GB, ~3.4 GB) can be used for higher precision.

What GPU do you need for glm ocr crispembed?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (2.6 GB file, about 3.4 GB in use).

Which glm ocr crispembed quant should you choose?

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

Architectureglm_ocr_ref
Parameters1.11B

Source

Quantized bycstr
FamilyGLM
Licenseother
Downloads (HF)1,816
Last updated2026-08-07

Frequently asked questions about glm ocr crispembed

How much VRAM does glm ocr crispembed need?

About 0.6 GB at its main file with an 8K context window. That is the 0.1 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 crispembed on an 8 GB GPU?

Yes, with F16: the 2.6 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of glm ocr crispembed GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, file is 0.1 GB, file is 0.1 GB, Q4_K is 0.9 GB and 2 more.

Where can I download glm ocr crispembed GGUF?

The files are on Hugging Face in the cstr/glm-ocr-crispembed-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 crispembed 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 this model on 8 GB VRAM?

Yes, the Q4_K quantization requires about 1.5 GB of VRAM at 8k context.

Does this model support multiple languages?

No, the language list is empty in the provided data.

What license applies to this model?

The model is released under the GLM‑4 Model Licence, not Apache‑2.0.

Similar models

Browse all →

More from cstr

All by cstr →

More GLM models

All GLM →

Other tiny models

All tiny models →