---
library_name: transformers
pipeline_tag: text-generation
tags:
- glm4_moe
- AWQ
- FP16Mix
- quantization fix
- vLLM
base_model:
- zai-org/GLM-4.5-Air
base_model_relation: quantized
---
# GLM-4.5-Air-AWQ-FP16Mix
Base model: [zai-org/GLM-4.5-Air](https://huggingface.co/zai-org/GLM-4.5-Air)
### 【vLLM Single Node with 8 GPUs Startup Command】
Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs.
```
CONTEXT_LENGTH=32768
vllm serve \
QuantTrio/GLM-4.5-Air-AWQ-FP16Mix \
--served-model-name GLM-4.5-Air-AWQ-FP16Mix \
--enable-expert-parallel \
--swap-space 16 \
--max-num-seqs 512 \
--max-model-len $CONTEXT_LENGTH \
--max-seq-len-to-capture $CONTEXT_LENGTH \
--gpu-memory-utilization 0.9 \
--tensor-parallel-size 8 \
--trust-remote-code \
--disable-log-requests \
--host 0.0.0.0 \
--port 8000
```
### 【Dependencies】
```
vllm==0.10.0
```
### 【❗❗Temporary Patch for vllm==0.10.0❗❗】
The `awq_marlin` module in `vllm` misses checking the `modules_to_not_convert` parameter when loading AWQ-MoE modules, which causes mixed quantization of MoE to fail or report errors.
Refer to: [[Issue #21888]](https://github.com/vllm-project/vllm/pull/21888)
Before the PR is merged, temporarily replace `awq_marlin.py` in `vllm/model_executor/layers/quantization/awq_marlin.py`.
### 【Model Update Date】
```
2025-07-30
1. Initial commit
```
### 【Model Files】
| File Size | Last Updated |
|-----------|--------------|
| `69GB` | `2025-07-30` |
### 【Model Download】
```python
from huggingface_hub import snapshot_download
snapshot_download('QuantTrio/GLM-4.5-Air-AWQ-FP16Mix', cache_dir="your_local_path")
```
### 【Overview】
# GLM-4.5
👋 Join our WeChat group .
📖 Read the GLM-4.5 technical blog .
📍 Access GLM-4.5 API via the ZhipuAI Open Platform .
👉 Try it online at GLM-4.5 .
## Model Introduction
The **GLM-4.5** model series is a foundation model designed for agents. GLM-4.5 has **355 billion** total parameters, of which **32 billion** are active. GLM-4.5-Air adopts a more compact design with **106 billion** total parameters and **12 billion** active parameters. The GLM-4.5 models unify reasoning, encoding, and agent capabilities to meet the complex demands of agent applications.
Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that offer two modes: a *thinking mode* for complex reasoning and tool use, and a *non-thinking mode* for instant responses.
We have open-sourced the base models, hybrid reasoning models, and FP8 versions of GLM-4.5 and GLM-4.5-Air. They are released under the MIT license and can be used for commercial purposes and secondary development.
In our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieved an excellent score of **63.2**, ranking **3rd** among all proprietary and open-source models. Notably, GLM-4.5-Air maintained strong efficiency while achieving a competitive score of **59.8**.
For more detailed evaluation results, demo cases, and technical information, please visit our [technical blog](https://z.ai/blog/glm-4.5). The full technical report will be released soon.
Model code, tool parsers, and inference parsers can be found in the following implementations:
- [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)
- [SGLang](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/glm4_moe.py)
## Quick Start
Please refer to our [GitHub project](https://github.com/zai-org/GLM-4.5). 