GLM 4.5 Air 0.72B MTP is an open-source language model by inference-optimization. Features: 0.72b LLM, VRAM: 1.4GB, Context: 128K, License: mit, LLM Explorer Score: 0.27.
| LLM Name | GLM 4.5 Air 0.72B MTP |
| Repository π€ | https://huggingface.co/inference-optimization/GLM-4.5-Air-0.72B-MTP |
| Model Size | 0.72b |
| Required VRAM | 1.4 GB |
| Updated | 2026-10-10 |
| Maintainer | inference-optimization |
| Model Type | glm4_moe |
| Model Files | |
| Model Architecture | Glm4MoeForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 5.17.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151552 |