GLM-OCR
👋 Join our WeChat and Discord community 📍 Use GLM-OCR's API 👉 GLM-OCR SDK Recommended 📖 Technical Report
Params
1.3 B
Context
—
Downloads 30d
2.0 M
Likes
2,024
Download history
daily snapshots · 106 days
▲ 0 in the last 30 days (0.0%)
2.0 M2.0 M
Oct 12Oct 22Nov 1Nov 10
3.3 M2.0 M
Aug 13Sep 12Oct 12Nov 10
3.8 M2.0 M
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 2.7 GB | 3.6 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- GlmOcrForConditionalGeneration
- Parameters
- 1.3 B
- Tensor type
- BF16
- Licence
- mit
- First seen on the Hub
- 2026-01-30
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any image-text-to-text model