LLMs · Zhipu AI
GLM-5.1 (744B-A40B)
- Parameters
- 754B (40.0B active)
- Architecture
- Mixture of experts
- Max context
- 198K tokens
- License
- mit
- Released
- 2026-04
How to run it
Ollama
Ollama only offered this as a cloud model, and has since retired it. To run it locally, use the GGUF files below with llama.cpp or LM Studio.
Quantized files · GGUF
Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.
huggingface.co/unsloth/GLM-5.1-GGUF (opens in a new tab)
ollama run hf.co/unsloth/GLM-5.1-GGUFOriginal weights · Hugging Face
Full-precision files from Zhipu AI, for fine-tuning, vLLM, Transformers.
Official repo · GitHub
Reference code, inference scripts and docs from Zhipu AI. The weights themselves download from Hugging Face.
github.com/zai-org/GLM-5 (opens in a new tab)
git clone https://github.com/zai-org/GLM-5Memory needed
Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.
| Quantization | Quality | Weights | Total at 8K context | Total at 32K context | Download |
|---|---|---|---|---|---|
Q2_K |
Low | 302 GB | 303 GB | 305 GB | GGUF (UD-Q2_K_XL) · folder (opens in a new tab) |
Q3_K_M |
Low | 369 GB | 371 GB | 373 GB | GGUF · folder (opens in a new tab) |
Q4_K_M |
Good | 460 GB | 461 GB | 463 GB | GGUF · folder (opens in a new tab) |
Q5_K_M |
High | 535 GB | 537 GB | 539 GB | GGUF · folder (opens in a new tab) |
Q6_K |
High | 618 GB | 620 GB | 622 GB | GGUF · folder (opens in a new tab) |
Q8_0 |
Very high | 799 GB | 800 GB | 803 GB | GGUF · folder (opens in a new tab) |
F16 |
Full | 1,508 GB | 1,509 GB | 1,511 GB | GGUF · folder (opens in a new tab) Original weights (opens in a new tab) |
Best hardware for GLM-5.1 (744B-A40B)
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.0/45, Memory fit 24.0/25, Speed 10.0/15, Memory use 15.0/15 | Apple M3 Ultra (512 GB) | Q2_K | 334 GB / 384 GB | 17.8 tok/s | Tight fit |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.