GLM-4.7 / GLM-Z1 — local AI model by Zhipu AI (Z.ai)
Written by Jakub Rusinowski · Last updated
Zhipu AI — rebranded internationally as Z.ai — released this February 2026 MoE model. GLM-4.7 uses a 32B active MoE architecture and scores on par with Claude Opus 4.5 on hallucination leaderboards. The reasoning-focused GLM-Z1 variant posts near-GPT-5.2 scores on the Artificial Intelligence Index. Strong multilingual support with particular depth in Chinese.
Variants
The smallest GLM-4.7 / GLM-Z1 variant needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| GLM-4 9B → 9B | ~6.2 GB | 128,000 | ollama run glm4:9b | |
| GLM-Z1 32B (Reasoning) → 32B | ~20.1 GB | 128,000 | ollama run glm-z1:32b | |
| GLM-4.7-Flash 30B-A3B → 30B (3B active) | ~18.9 GB | 198,000 | ollama run glm-4.7-flash |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run GLM-4.7 / GLM-Z1 locally
Install Ollama, then pull the tag.
ollama run glm4:9bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: GLM-4 9B, GLM-Z1 32B (Reasoning)Commercial use permitted. No usage restrictions beyond attribution.
Applies to: GLM-4.7-Flash 30B-A3BRecommended GPU
The cheapest catalogued GPU that runs GLM-4.7 / GLM-Z1 locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run GLM-4.7 / GLM-Z1 on my GPU?
- GLM-4.7 / GLM-Z1 on AMD Radeon RX 7900 XT
- GLM-4.7 / GLM-Z1 on AMD Radeon RX 7900 XTX
- GLM-4.7 / GLM-Z1 on AMD Radeon RX 9060 XT 8GB
- GLM-4.7 / GLM-Z1 on Apple M1 Pro
- GLM-4.7 / GLM-Z1 on Apple M2 Pro
- GLM-4.7 / GLM-Z1 on Apple M3 Pro
- GLM-4.7 / GLM-Z1 on Apple M4
- GLM-4.7 / GLM-Z1 on Apple M5
- GLM-4.7 / GLM-Z1 on Intel Arc B570
- GLM-4.7 / GLM-Z1 on Intel Arc B580
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 3060 (12GB)
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 3070
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 3070 Ti
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 3080 (10GB)
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 3090
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 4060
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 4070
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 4070 Super
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 4070 Ti
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 4090
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 5060
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 5060 Ti 8GB
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 5070
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 5090
- GLM-4.7 / GLM-Z1 on NVIDIA L40S
- GLM-4.7 / GLM-Z1 on NVIDIA RTX 6000 Ada Generation
GLM-4.7 / GLM-Z1 — frequently asked questions
How much VRAM does GLM-4.7 / GLM-Z1 need?
GLM-4.7 / GLM-Z1 needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-4 9B (6 GB, Q4_K_M); GLM-Z1 32B (Reasoning) (20 GB, Q4_K_M); GLM-4.7-Flash 30B-A3B (19 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run GLM-4.7 / GLM-Z1 on an RTX 4090 (24 GB)?
Yes — GLM-4.7 / GLM-Z1 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-4.7 / GLM-Z1?
Q4_K_M is the best balance of quality and VRAM for GLM-4.7 / GLM-Z1 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-4.7 / GLM-Z1 with Ollama?
Install Ollama, then run: ollama run glm4:9b. This downloads GLM-4.7 / GLM-Z1 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.