GLM-6 — Local AI Model by Zhipu AI

作者： Jakub Rusinowski · 最后更新： 2026年7月10日

PREVIEW (June 2026, specs unverified). Zhipu/Z.AI's sixth-generation series — a frontier MoE flagship plus a consumer-scale dense model, MIT-licensed, agentic/long-context focused. Numbers carried from the GLM-5 lineage; verify against the Hugging Face org page.

Hardware Requirements

GLM-6 9BMin 6 GB VRAM · Q4_K_M · 128,000 ctx ·
GLM-6 355B-A32BMin 215 GB VRAM · Q4_K_M · 200,000 ctx ·

Recommended GPU

The cheapest GPU that runs GLM-6 locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。
Intel Arc B570 10GB
首发建议零售价：$219
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

How to Run Locally

Install Ollama then run: ollama run

Minimum VRAM: 6 GB. For best results use Q4_K_M quantization.

GLM-6 — Frequently Asked Questions

How much VRAM does GLM-6 need?

GLM-6 needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-6 9B (6 GB, Q4_K_M); GLM-6 355B-A32B (215 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run GLM-6 on an RTX 4090 (24 GB)?

Yes — GLM-6 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for GLM-6?

Q4_K_M is the best balance of quality and VRAM for GLM-6 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-6 with Ollama?

Install Ollama, then run: ollama run . This downloads GLM-6 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.

Can I Run GLM-6 on My GPU?