GLM-OCR
Suverenost i hosting
Ovaj je model u katalogu za referencu. Još nije hostan na LLM EU i nijedna vlastita krajnja točka ga ovdje ne poslužuje. Zahtjevi za njega idu izravno pružatelju, prema uvjetima tog pružatelja.
Sažetak
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.
Specifikacije
- Pružatelj
- Z.ai (Zhipu AI) (CN)
- Kontekstni prozor
- 131k
- Parametri
- 1.33B
- Modaliteti
- vision
- Licenca
- mit · licence
- Otvoreni utezi
- yes
- Datum izlaska
- 30. sij 2026.
- Zadaci
- vision, rag, legal-draft, cheap, summarization
Jezici
Jako: zh, en
Zadovoljavajuće: de, fr, es, ru, ja, ko
Jezici
Jako
- zh
- en
Zadovoljavajuće
- de
- fr
- es
- ru
- ja
- ko
Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Kada ga koristiti
Prednosti
- purpose-built document OCR rather than general vision
- runs on modest hardware and through common inference servers
- MIT licence
Ograničenja
- 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