cstr/glm-ocr-crispembed-GGUF overview
GLM OCR CrispEmbed GGUF GLM Edge V 2B vision language model converted to GGUF for OCR with CrispEmbed https://github.com/CrispStrobe/CrispEmbed . Models | File…
Runs locally from ~15.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| glm-ocr-f16.gguf | GGUF | F16 | 2.40 GB | Download |
| glm-ocr-layer12-ref.gguf | GGUF | GGUF | 20.3 MB | Download |
| glm-ocr-layer14-ref.gguf | GGUF | GGUF | 20.3 MB | Download |
| glm-ocr-q4_k.gguf | GGUF | Q4_K | 848.3 MB | Download |
| glm-ocr-q8_0.gguf | GGUF | Q8_0 | 1.10 GB | Download |
| glm-ocr-ref-4layer.gguf | GGUF | GGUF | 15.3 MB | Download |
| glm-ocr-ref-full.gguf | GGUF | GGUF | 60.3 MB | Download |
Model Details
Model README
---
license: apache-2.0
tags:
- ocr
- vlm
- document-understanding
- gguf
- crispembed
library_name: crispembed
base_model: THUDM/glm-edge-v-2b
---
GLM-OCR CrispEmbed GGUF
GLM-Edge-V 2B vision-language model converted to GGUF for OCR with CrispEmbed.
Models
| File | Quant | Size |
|------|-------|------|
| glm-ocr-f16.gguf | F16 | ~3.8 GB |
| glm-ocr-q8_0.gguf | Q8_0 | ~2.0 GB |
| glm-ocr-q4_k.gguf | Q4_K | ~1.1 GB |
Architecture
- Base: GLM-Edge-V 2B (THUDM, Apache-2.0)
- Vision: SigLIP vision encoder
- LLM: GLM-4 decoder (2B params)
- Task: Document OCR, scene text, handwriting
Usage
from crispembed import CrispOcrPipeline
ocr = CrispOcrPipeline(vlm_model="glm-ocr-q8_0.gguf")
text = ocr.recognize("document.png")Original Model
THUDM/glm-edge-v-2b — GLM-Edge-V 2B, CogViT + GLM-0.5B, 8 languages.
License
Apache-2.0
Run cstr/glm-ocr-crispembed-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models