GLM-OCR
Sovranità u hosting
Dan il-mudell huwa katalogat għal referenza. Mhuwiex ospitat fuq LLM EU bħalissa, u l-ebda endpoint tal-ewwel parti ma jservih hawn. Talbiet lejh imorru direttament għand il-fornitur, taħt it-termini tal-fornitur stess.
Sommarju
GLM-OCR is a small multimodal model for document text extraction, built from a CogViT vision encoder and a GLM-0.5B language decoder. The vendor states it has about 0.9B parameters while the published safetensors total is 1.33B, and the configuration allows 131,072 text positions. It is MIT licensed and runs under vLLM, SGLang or Ollama for high-volume extraction.
Speċifikazzjonijiet
- Fornitur
- Z.ai (Zhipu AI) (CN)
- Tieqa tal-kuntest
- 131k
- Parametri
- 1.33B
- Modalitajiet
- vision
- Liċenza
- mit · licence
- Piżijiet miftuħa
- yes
- Data tal-ħruġ
- 30 Jan 2026
- Kompiti
- vision, rag, legal-draft, cheap, summarization
Lingwi
Qawwi: zh, en
Adekwat: de, fr, es, ru, ja, ko
Lingwi
Qawwi
- zh
- en
Adekwat
- de
- fr
- es
- ru
- ja
- ko
Mhux verifikat: il-fornitur ma dokumentax din id-dikjarazzjoni. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Meta tużaha
Saħħiet
- purpose-built document OCR rather than general vision
- runs on modest hardware and through common inference servers
- MIT licence
Limiti
- text extraction only; it is not a general chat or reasoning model
- vendor parameter count (0.9B) differs from the published safetensors total (1.33B)
- no OCR benchmark has been run by LLM EU