---
license: mit
language:
- en
- zh
pipeline_tag: text-generation
library_name: transformers
base_model:
- zai-org/GLM-4.5-Air
---
# GLM-4.5-Air-AWQ
## Method
Quantised using [vllm-project/llm-compressor](https://github.com/vllm-project/llm-compressor.git), [nvidia/Llama-Nemotron-Post-Training-Dataset](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset) and the following configs:
```
config_groups = {
"group_0": {
"targets": ["Linear"],
"input_activations": None,
"output_activations": None,
"weights": {
"num_bits": 4,
"type": "int",
"symmetric": True,
"strategy": "group",
"group_size": 32,
}
}
}
recipe = [
AWQModifier(
ignore=["lm_head", "re:.*mlp.gate$"],
config_groups=config_groups,
),
]
```
Note: the last layer, i.e., the MTP layer index 46 is ignored due to transformers not having MTP implementations.
## Inference
### Prerequisite
Install the latest vllm version:
```
pip install -U vllm \
--pre \
--extra-index-url https://wheels.vllm.ai/nightly
```
### vllm
Please load the model into vllm and sglang as float16 data type for AWQ support and use `tensor_parallel_size <= 2` i.e.,
```
vllm serve cpatonn/GLM-4.5-Air-AWQ --dtype float16 --tensor-parallel-size 2 --pipeline-parallel-size 2
```
# GLM-4.5-Air
👋 Join our Discord community.
📖 Check out the GLM-4.5 technical blog.
📍 Use GLM-4.5 API services on Z.ai API Platform (Global) or
Zhipu AI Open Platform (Mainland China).
👉 One click to GLM-4.5.
## Model Introduction
The **GLM-4.5** series models are foundation models designed for intelligent agents. GLM-4.5 has **355** billion total parameters with **32** billion active parameters, while GLM-4.5-Air adopts a more compact design with **106** billion total parameters and **12** billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.
Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that provide two modes: thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses.
We have open-sourced the base models, hybrid reasoning models, and FP8 versions of the hybrid reasoning models for both GLM-4.5 and GLM-4.5-Air. They are released under the MIT open-source license and can be used commercially and for secondary development.
As demonstrated in our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieves exceptional performance with a score of **63.2**, in the **3rd** place among all the proprietary and open-source models. Notably, GLM-4.5-Air delivers competitive results at **59.8** while maintaining superior efficiency.
For more eval results, show cases, and technical details, please visit
our [technical blog](https://z.ai/blog/glm-4.5). The technical report will be released soon.
The model code, tool parser and reasoning parser can be found in the implementation of [transformers](https://github.com/huggingface/transformers/tree/main/src/transformers/models/glm4_moe), [vLLM](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/glm4_moe_mtp.py) and [SGLang](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/glm4_moe.py).
## Quick Start
Please refer our [github page](https://github.com/zai-org/GLM-4.5) for more detail. 