GLM-5.2 — lokalny model AI od Zhipu AI (Z.ai)
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
Z.ai's June 2026 flagship and, by Artificial Analysis' ranking at the time, the strongest open-weight model available — fourth overall including closed models. A 744B-parameter Mixture-of-Experts with roughly 40B active per token and a genuinely usable 1M-token input context (output up to 131,072). Two selectable reasoning-effort levels. Released in stages between 13 and 17 June 2026: the Coding Plan first, then open weights on Hugging Face, then documentation. The MIT license is the notable part — full commercial use, modification and redistribution on a frontier-scale model.
Warianty
Najmniejszy wariant GLM-5.2 potrzebuje około 450 GB VRAM przy Q4_K_M — skwantyzowane wagi plus narzut frameworka, bez pamięci podręcznej KV.
| Model | VRAM przy Q4 | VRAM | Kontekst | Uruchom |
|---|---|---|---|---|
| GLM-5.2 744B → 744B (~40B active) | ~450 GB | 1,000,000 | ollama run glm-5-2 |
Pamięć to skwantyzowane wagi plus narzut przy Q4_K_M, liczone tym samym silnikiem co sprawdzarka GPU i VRAM.
Jak uruchomić GLM-5.2 lokalnie
Zainstaluj Ollama, a potem pobierz tag.
ollama run glm-5-2Wybierz rozmiar powyżej, aby zobaczyć jego VRAM, szacowaną szybkość i polecenie instalacji.
Licencja
Commercial use permitted. No usage restrictions beyond attribution.
Dotyczy: GLM-5.2 744BCzy uruchomię GLM-5.2 na moim GPU?
GLM-5.2 — najczęściej zadawane pytania
How much VRAM does GLM-5.2 need?
GLM-5.2 needs about 450 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-5.2 744B (450 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run GLM-5.2 on an RTX 4090 (24 GB)?
GLM-5.2's smallest variant needs about 450 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for GLM-5.2?
Q4_K_M is the best balance of quality and VRAM for GLM-5.2 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run GLM-5.2 with Ollama?
GLM-5.2 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.