GLM 4.5 Air GPTQ Int4 Int8Mix is an open-source language model by QuantTrio. Features: 19.8b LLM, VRAM: 70.9GB, Context: 128K, Quantized, LLM Explorer Score: 0.24.
| LLM Name | GLM 4.5 Air GPTQ Int4 Int8Mix |
| Repository π€ | https://huggingface.co/QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix |
| Base Model(s) | |
| Model Size | 19.8b |
| Required VRAM | 70.9 GB |
| Updated | 2026-08-05 |
| Maintainer | QuantTrio |
| Model Type | glm4_moe |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Glm4MoeForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.54.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151552 |
| Torch Data Type | float16 |