GLM-4.5
GLM-4.5 is an open-weights language model from Z.ai, released July 28, 2025. It has 358B parameters (mixture-of-experts, 39B active). The context window is 128K tokens. API price: $0.6 input / $2.2 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 locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. 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 | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: unsloth/GLM-4.5-GGUF · bartowski/zai-org_GLM-4.5-GGUF · lmstudio-community/GLM-4.5-GGUF · ubergarm/GLM-4.5-GGUF · DevQuasar/zai-org.GLM-4.5-GGUF · anikifoss/GLM-4.5-HQ4_K
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| Humanity's Last Exam | 8.3% |
Links
Announcement · Hugging Face: zai-org/GLM-4.5 · 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