GLM-4.5-Air
GLM-4.5-Air is an open-weights language model from Z.ai, released July 20, 2025. It has 110B parameters (mixture-of-experts, 17B active). The context window is 128K tokens. API price: $0.2 input / $1.1 output per million tokens.
We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes.
Check it against your own PC →
Can you run GLM-4.5-Air locally?
The smallest common GPU it runs on is 8 GB of VRAM (with 32 GB of RAM): IQ2_XXS, GPU + experts in RAM, roughly 14 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Runs · GPU + CPU experts | IQ2_XXS (heavy loss) | 7.2 GB | 24.9 GB | ~14 |
| 12 GB VRAM | Runs · GPU + CPU experts | IQ2_XXS (heavy loss) | 11.2 GB | 20.9 GB | ~16 |
| 16 GB VRAM | Runs · GPU + CPU experts | IQ2_M (heavy loss) | 15.2 GB | 25.8 GB | ~14 |
| 24 GB VRAM | Runs · GPU + CPU experts | IQ3_XXS (noticeable loss) | 23.2 GB | 22.7 GB | ~17 |
| 32 GB VRAM | Runs · GPU + CPU experts | IQ3_XXS (noticeable loss) | 31.2 GB | 14.7 GB | ~26 |
Ready-made quantizations on Hugging Face: unsloth/GLM-4.5-Air-GGUF · bartowski/zai-org_GLM-4.5-Air-GGUF · auRose94/GLM-4.5-Air-ninths-k63-e99-GGUF · ggml-org/GLM-4.5-Air-GGUF · steampunque/GLM-4.5-Air-MP-GGUF · lmstudio-community/GLM-4.5-Air-GGUF
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| Humanity's Last Exam | 8.1% |
Links
Announcement · Hugging Face: zai-org/GLM-4.5-Air · Epoch AI benchmarks
More from Z.ai
GLM-5.3-FlashX · GLM 5.3 Flash BF16 · GLM 5.3 BF16 · GLM-5.3-Flash · GLM-5.3 · GLM-5.2 · GLM-5.1 · GLM-5V-Turbo