The real cost to run GLM 5.2

zai-org · 753.3B parameters · 1M context · commercial OK

GLM 5.2 — 753.3B params (zai-org). Auto-indexed from the Hugging Face Hub (33,589 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run GLM 5.2 — $0 markup

• On your own machine — $0. Runs free locally if you have about 538 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
• On your own rented GPU — from $11.12/hr. 8× NVIDIA A100 80GB at the direct RunPod price (≈ $10.36 a session), $0 markup.
• Via your own API key — $2.50/1M tokens (blended input + output). No GPU to manage (real price, 2026-06-22).

Key facts

Open the free Spanvero advisor → for the live, interactive math for your exact workload and hardware.

Related models

• GLM 4.7 Flash — 31.2B, zai-org
• GLM 4.5 Air — 110.5B, zai-org
• GLM 4.5 — 358.3B, zai-org
• GLM 5.1 — 753.9B, zai-org
• GLM 5 — 753.9B, zai-org

Browse: More Z.ai (GLM) models · All models · Compare

Spanvero · What's new · Prices as of 2026-06-22. We're an honest advisor — $0 markup, your own accounts, we never resell compute. © 2026 Cynosure LLC.